{ "data": { "a": { "slug": "serphouse", "name": "SERPHouse", "vendor": "Patoliya Infotech LLP", "vendorUrl": "https://www.serphouse.com", "kind": "http-api", "category": "search", "summary": "SERPHouse is a SERP API from Patoliya Infotech LLP in India that returns parsed Google, Bing and Yahoo results as JSON, live or scheduled, with a Scraper API for page HTML or Markdown and a hosted MCP server.", "url": "https://www.anchorterminal.com/tools/serphouse", "markdownUrl": "https://www.anchorterminal.com/tools/serphouse.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/serphouse.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/serphouse.json", "dns": "serphouse.grade.anchorterminal.com", "repo": "https://github.com/SERPHouse/serphouse-mcp", "transports": [ "streamable-http", "stdio" ], "remoteUrl": "https://mcp.serphouse.com/YOUR_API_KEY/mcp", "packages": [ { "registry": "npm", "name": "serphouse-mcp" } ], "auth": "api-key", "authNotes": "One API key per account, shown on the dashboard after a browser signup and email confirmation. Sent as `Authorization: Bearer` or as `api_token` in the query string. The hosted MCP server takes the key in its URL path. One account per user. No scopes or rotation found.", "pricing": "paid", "pricingNotes": "Basic $29.99 a month for 400,000 credits ($0.75 per 1,000 SERP requests) and Regular $49.99 for 800,000 ($0.62). Autocomplete $0.37 and $0.31, Top 100 Google $7.50 and $6.25 per 1,000. Custom plans by email. Free trial 4,000 credits for 7 days, no card. Credits don't roll over.", "priceSummary": "$0.75 / 1k req", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the pricing page, the docs, llms.txt or the MCP source (checked 2026-11-06). An empty balance returns 402 'Insufficient credits'.", "endpoints": [] }, "toolCount": 23, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://www.serphouse.com/docs", "llmsTxt": "https://www.serphouse.com/llms.txt", "capabilities": [ "search.serp", "web.search", "search.news", "search.images", "web.fetch" ], "tags": [ "hosted", "paid", "no-card", "free-tier", "mcp", "remote-mcp", "llms-txt", "python", "india" ], "lastRelease": "2026-07-06", "graded": true, "anchor": { "graded": true, "score": 42.4, "grade": "E", "agentReady": false, "rank": 1283, "ranked": true, "rankOf": 1510, "categoryRank": 24, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 64, "maintenance": 23, "payments": 40, "reliability": 40, "schema": 66, "security": 11, "transparency": 50 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "SERPHouse returns parsed Google, Bing and Yahoo results at published prices from $0.62 per 1,000 requests, with a 23-tool MCP server and a 4,000-credit trial without a card. The hosted MCP puts the key in its URL, there is no status page, changelog or security contact, and the terms keep search history indefinitely.", "bestFor": "Low-cost Google, Bing and Yahoo result parsing for SEO and rank tracking, with many Google verticals.", "strengths": [ "Published prices per 1,000 requests, $0.75 on Basic and $0.62 on Regular, with failed requests not charged", "Google web, news, images, shopping, jobs, videos, forums, local and autocomplete, plus Bing and Yahoo, in one API", "Hosted and stdio MCP server with 23 tools, typed Zod inputs and routing advice between tools, MIT licensed", "llms.txt and Markdown copies of the docs pages, with a status code table and per-engine examples", "Free trial of 4,000 credits for 7 days with no card" ], "weaknesses": [ "The hosted MCP server takes the API key only in its URL path, and the REST API also accepts `api_token` in the query string", "No status page, changelog, security.txt, disclosure policy or certification found", "Terms keep search history indefinitely and advise users in the European Economic Area not to use the service", "The pricing page states a 99.99% uptime SLA and the docs 99.95%, with no SLA terms or credits found", "The home page sends readers to a playground 'on the Oxylabs dashboard', with no relationship to Oxylabs found" ], "agentNotes": [ "Send the key as `Authorization: Bearer`, not as `api_token` in the URL", "Treat a 200 with `\"status\": \"error\"` and 'Please try again' as a failure and retry later", "Pass `loc` or `loc_id` for Google and Bing tools other than `serphouse_search`; find IDs with `serphouse_location_search`", "Use `serphouse_search` for plain lookups and `serphouse_serp_google_advanced` only when ranks beyond the top 10 are needed, at ten times the price", "Keep under 60 requests a minute on self-serve plans" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 42.4 } ], "editorialScores": { "ergonomics": 64, "maintenance": 23, "payments": 40, "reliability": 40, "schema": 66, "security": 11, "transparency": 39 }, "provenanceScore": 61, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npx serphouse-mcp", "http": "curl -X POST https://api.serphouse.com/serp/live \\\n -H 'accept: application/json' \\\n -H 'authorization: Bearer API_TOKEN' \\\n -H 'content-type: application/json' \\\n -d '{\"data\": {\"domain\": \"google.com\", \"lang\": \"en\", \"q\": \"Coffee\", \"loc\": \"Texas,United States\", \"device\": \"desktop\", \"serp_type\": \"web\"}}'", "config": { "mcpServers": { "serphouse": { "url": "https://mcp.serphouse.com/YOUR_SERPHouse_API_KEY/mcp" } } } }, "letme": { "capability": "https://letme.dev/search.serp", "tool": "https://letme.dev/serphouse" }, "area": "web-data", "unitPrices": [ { "item": "SERP request, Basic", "unit": "1k-requests", "usd": 0.75, "note": "$29.99 a month for 400,000 credits" }, { "item": "SERP request, Regular", "unit": "1k-requests", "usd": 0.62, "note": "$49.99 a month for 800,000 credits" }, { "item": "Autocomplete request, Basic", "unit": "1k-requests", "usd": 0.37, "note": "$0.31 on Regular" }, { "item": "Top 100 Google SERP, Basic", "unit": "1k-requests", "usd": 7.5, "note": "$6.25 on Regular" }, { "item": "Basic plan", "unit": "month", "usd": 29.99, "note": "400,000 credits, no rollover" }, { "item": "Regular plan", "unit": "month", "usd": 49.99, "note": "800,000 credits, no rollover" } ], "provenance": { "legalEntity": "Patoliya Infotech LLP", "domain": "serphouse.com", "domainRegistered": "2019-08-20", "endpointOnVendorDomain": true, "terms": "https://www.serphouse.com/terms-of-service", "privacy": "https://www.serphouse.com/privacy-policy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The terms name Patoliya Infotech LLP, a limited liability partnership incorporated in India, under Indian law with courts in Surat. The contact page gives an address in Utran, Surat, Gujarat.", "No effective or updated date was found on the terms or the privacy policy.", "www.serphouse.com/robots.txt allows all agents except /data/.", "The trial terms forbid 'scraping at scale or performing automated bulk data extraction' with trial credits. No clause on automated access to the website was found.", "/.well-known/security.txt answers 404. No status page is linked, and status.serphouse.com did not answer.", "RDAP gives serphouse.com a registration date of 20 August 2019; the about page says SERPHouse started in September 2019." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/serphouse.json", "live": { "slug": "serphouse", "probe": { "target": "https://mcp.serphouse.com/YOUR_API_KEY/mcp", "method": "get", "lastAt": "2026-11-07T19:22:32.462161347Z", "lastOk": true, "lastStatus": 400, "lastMs": 260, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 236, "p95ms24h": 348, "samples24h": 210, "samples30d": 210, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "versions": [ { "registry": "github", "name": "SERPHouse/serphouse-mcp", "version": "1.1.0", "released": "2026-07-06", "seenAt": "2026-11-07T00:04:55.526969474Z" }, { "registry": "npm", "name": "serphouse-mcp", "version": "1.1.0", "seenAt": "2026-11-07T00:04:54.741719814Z" } ], "githubStars": 10, "npmWeekly": 11, "securityTxt": { "url": "https://serphouse.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T15:59:39.38860304Z" }, "llmsTxt": { "url": "https://www.serphouse.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:33:54.600324581Z" }, "pages": [ { "url": "https://www.serphouse.com/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:34:21.531839335Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "85f9c0a9e291" }, { "url": "https://www.serphouse.com/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:34:24.703890347Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "171892dff54e" } ], "mcpTools": { "url": "https://mcp.serphouse.com/YOUR_SERPHouse_API_KEY/mcp", "checkedAt": "2026-11-07T01:47:41.660458875Z", "status": "ok", "protocol": "2025-11-25", "tools": [ { "name": "serphouse_domain_list", "title": "Serphouse Domain List", "description": "List supported search domains. Call this before Yahoo searches — yahoo.com is not valid; use regional domains like uk.yahoo.com from this list.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": {}, "type": "object" } }, { "name": "serphouse_language_list", "title": "Serphouse Language List", "description": "Get supported language codes for google, bing, or yahoo.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "type": { "description": "Search engine language catalog to fetch.", "enum": [ "google", "bing", "yahoo" ], "type": "string" } }, "required": [ "type" ], "type": "object" } }, { "name": "serphouse_location_search", "title": "Serphouse Location Search", "description": "Search Serphouse location ids and location strings for Google or Bing targeting.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "q": { "description": "Location search term, for example texas or london.", "minLength": 1, "type": "string" }, "type": { "default": "google", "enum": [ "google", "bing" ], "type": "string" } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_account_info", "title": "Serphouse Account Info", "description": "Get Serphouse account plan and credit usage.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": {}, "type": "object" } }, { "name": "serphouse_search", "title": "Serphouse Search", "description": "Default web search for agents — fast lightweight Google organic results via POST /web-search-lite. Only q is required; gl defaults to US. Use serphouse_google_web only when you need device, gfilter, or num_result. Use serphouse_serp_google_advanced for SEO rankings beyond top 10.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "date_range": { "description": "Optional date filter: YYYY-MM-DD,YYYY-MM-DD or one of h, d, w, m, y. Omit for general searches — lite results may be empty when this is set.", "minLength": 1, "type": "string" }, "domain": { "default": "google.com", "minLength": 1, "type": "string" }, "gl": { "description": "Two-letter ISO country code, e.g. US, IN, GB. Used when loc is omitted.", "minLength": 1, "pattern": "^[A-Za-z]{2}$", "type": "string" }, "lang": { "default": "en", "minLength": 1, "type": "string" }, "loc": { "description": "Location name, e.g. Austin,Texas,United States. Provide loc or gl, not both.", "minLength": 1, "type": "string" }, "no_trace": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" }, { "const": "true", "type": "string" }, { "const": "false", "type": "string" }, { "const": true, "type": "boolean" }, { "const": false, "type": "boolean" } ], "description": "Enterprise only. Enables NoTrace mode when set to 1 or true." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" }, "verbatim": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" } ] } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_google_web_lite", "title": "Serphouse Google Web Search (Lite)", "description": "Alias of serphouse_search — fast lightweight Google organic results via POST /web-search-lite. Prefer serphouse_search for general agent queries.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "date_range": { "description": "Optional date filter: YYYY-MM-DD,YYYY-MM-DD or one of h, d, w, m, y. Omit for general searches — lite results may be empty when this is set.", "minLength": 1, "type": "string" }, "domain": { "default": "google.com", "minLength": 1, "type": "string" }, "gl": { "description": "Two-letter ISO country code, e.g. US, IN, GB. Used when loc is omitted.", "minLength": 1, "pattern": "^[A-Za-z]{2}$", "type": "string" }, "lang": { "default": "en", "minLength": 1, "type": "string" }, "loc": { "description": "Location name, e.g. Austin,Texas,United States. Provide loc or gl, not both.", "minLength": 1, "type": "string" }, "no_trace": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" }, { "const": "true", "type": "string" }, { "const": "false", "type": "string" }, { "const": true, "type": "boolean" }, { "const": false, "type": "boolean" } ], "description": "Enterprise only. Enables NoTrace mode when set to 1 or true." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" }, "verbatim": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" } ] } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_google_web", "title": "Serphouse Google Web Search (Full)", "description": "Full Google web search via POST /google-web with device, gfilter, and num_result. Requires loc or loc_id. For general queries use serphouse_search instead.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "date_range": { "description": "Date range as YYYY-MM-DD,YYYY-MM-DD or one of h, d, w, m, y.", "minLength": 1, "type": "string" }, "device": { "default": "desktop", "enum": [ "desktop", "mobile" ], "type": "string" }, "domain": { "default": "google.com", "minLength": 1, "type": "string" }, "gfilter": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" } ] }, "lang": { "default": "en", "minLength": 1, "type": "string" }, "loc": { "description": "Required unless loc_id is provided. Location name, for example Austin,Texas,United States. Provide exactly one of loc or loc_id.", "minLength": 1, "type": "string" }, "loc_id": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, { "minLength": 1, "pattern": "^\\d+$", "type": "string" } ], "description": "Required unless loc is provided. Serphouse location id from serphouse_location_search. Provide exactly one of loc_id or loc." }, "no_trace": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" }, { "const": "true", "type": "string" }, { "const": "false", "type": "string" }, { "const": true, "type": "boolean" }, { "const": false, "type": "boolean" } ], "description": "Enterprise only. Enables NoTrace mode when set to 1 or true." }, "num_result": { "maximum": 10, "minimum": 1, "type": "integer" }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" }, "verbatim": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" } ] } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_google_image", "title": "Serphouse Google Image Search", "description": "Run a realtime Google image search via POST /google-image.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "date_range": { "minLength": 1, "type": "string" }, "domain": { "default": "google.com", "minLength": 1, "type": "string" }, "lang": { "default": "en", "minLength": 1, "type": "string" }, "loc": { "description": "Required unless loc_id is provided. Location name, for example Austin,Texas,United States. Provide exactly one of loc or loc_id.", "minLength": 1, "type": "string" }, "loc_id": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, { "minLength": 1, "pattern": "^\\d+$", "type": "string" } ], "description": "Required unless loc is provided. Serphouse location id from serphouse_location_search. Provide exactly one of loc_id or loc." }, "no_trace": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" }, { "const": "true", "type": "string" }, { "const": "false", "type": "string" }, { "const": true, "type": "boolean" }, { "const": false, "type": "boolean" } ], "description": "Enterprise only. Enables NoTrace mode when set to 1 or true." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_google_news", "title": "Serphouse Google News Search", "description": "Run a realtime Google news search via POST /google-news.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "date_range": { "minLength": 1, "type": "string" }, "device": { "default": "desktop", "enum": [ "desktop", "mobile" ], "type": "string" }, "domain": { "default": "google.com", "minLength": 1, "type": "string" }, "lang": { "default": "en", "minLength": 1, "type": "string" }, "loc": { "description": "Required unless loc_id is provided. Location name, for example Austin,Texas,United States. Provide exactly one of loc or loc_id.", "minLength": 1, "type": "string" }, "loc_id": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, { "minLength": 1, "pattern": "^\\d+$", "type": "string" } ], "description": "Required unless loc is provided. Serphouse location id from serphouse_location_search. Provide exactly one of loc_id or loc." }, "no_trace": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" }, { "const": "true", "type": "string" }, { "const": "false", "type": "string" }, { "const": true, "type": "boolean" }, { "const": false, "type": "boolean" } ], "description": "Enterprise only. Enables NoTrace mode when set to 1 or true." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_google_shop", "title": "Serphouse Google Shop Search", "description": "Run a realtime Google shopping search via POST /google-shop.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "domain": { "default": "google.com", "minLength": 1, "type": "string" }, "lang": { "default": "en", "minLength": 1, "type": "string" }, "loc": { "description": "Required unless loc_id is provided. Location name, for example Austin,Texas,United States. Provide exactly one of loc or loc_id.", "minLength": 1, "type": "string" }, "loc_id": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, { "minLength": 1, "pattern": "^\\d+$", "type": "string" } ], "description": "Required unless loc is provided. Serphouse location id from serphouse_location_search. Provide exactly one of loc_id or loc." }, "no_trace": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" }, { "const": "true", "type": "string" }, { "const": "false", "type": "string" }, { "const": true, "type": "boolean" }, { "const": false, "type": "boolean" } ], "description": "Enterprise only. Enables NoTrace mode when set to 1 or true." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_bing_web", "title": "Serphouse Bing Web Search", "description": "Run a realtime Bing web search via POST /bing-web.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "date_range": { "minLength": 1, "type": "string" }, "device": { "default": "desktop", "enum": [ "desktop", "mobile" ], "type": "string" }, "lang": { "default": "en-US", "description": "Language code, for example en-US or fr-FR.", "minLength": 1, "type": "string" }, "loc": { "description": "Required unless loc_id is provided. Location name, for example Austin,Texas,United States. Provide exactly one of loc or loc_id.", "minLength": 1, "type": "string" }, "loc_id": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, { "minLength": 1, "pattern": "^\\d+$", "type": "string" } ], "description": "Required unless loc is provided. Serphouse location id from serphouse_location_search. Provide exactly one of loc_id or loc." }, "no_trace": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" }, { "const": "true", "type": "string" }, { "const": "false", "type": "string" }, { "const": true, "type": "boolean" }, { "const": false, "type": "boolean" } ], "description": "Enterprise only. Enables NoTrace mode when set to 1 or true." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_bing_image", "title": "Serphouse Bing Image Search", "description": "Run a realtime Bing image search via POST /bing-image.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "lang": { "default": "en-US", "minLength": 1, "type": "string" }, "loc": { "description": "Required unless loc_id is provided. Location name, for example Austin,Texas,United States. Provide exactly one of loc or loc_id.", "minLength": 1, "type": "string" }, "loc_id": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, { "minLength": 1, "pattern": "^\\d+$", "type": "string" } ], "description": "Required unless loc is provided. Serphouse location id from serphouse_location_search. Provide exactly one of loc_id or loc." }, "no_trace": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" }, { "const": "true", "type": "string" }, { "const": "false", "type": "string" }, { "const": true, "type": "boolean" }, { "const": false, "type": "boolean" } ], "description": "Enterprise only. Enables NoTrace mode when set to 1 or true." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_bing_news", "title": "Serphouse Bing News Search", "description": "Run a realtime Bing news search via POST /bing-news.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "device": { "default": "desktop", "enum": [ "desktop", "mobile" ], "type": "string" }, "lang": { "default": "en-US", "minLength": 1, "type": "string" }, "loc": { "description": "Required unless loc_id is provided. Location name, for example Austin,Texas,United States. Provide exactly one of loc or loc_id.", "minLength": 1, "type": "string" }, "loc_id": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, { "minLength": 1, "pattern": "^\\d+$", "type": "string" } ], "description": "Required unless loc is provided. Serphouse location id from serphouse_location_search. Provide exactly one of loc_id or loc." }, "no_trace": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" }, { "const": "true", "type": "string" }, { "const": "false", "type": "string" }, { "const": true, "type": "boolean" }, { "const": false, "type": "boolean" } ], "description": "Enterprise only. Enables NoTrace mode when set to 1 or true." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_yahoo_web", "title": "Serphouse Yahoo Web Search", "description": "Run a realtime Yahoo web search via POST /yahoo-web.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "device": { "default": "desktop", "enum": [ "desktop", "mobile" ], "type": "string" }, "domain": { "default": "uk.yahoo.com", "description": "Regional Yahoo domain from serphouse_domain_list, for example uk.yahoo.com or fr.yahoo.com. Do not use yahoo.com.", "minLength": 1, "type": "string" }, "lang": { "default": "lang_en", "description": "Yahoo language code, for example lang_en or lang_fr.", "minLength": 1, "type": "string" }, "no_trace": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" }, { "const": "true", "type": "string" }, { "const": "false", "type": "string" }, { "const": true, "type": "boolean" }, { "const": false, "type": "boolean" } ], "description": "Enterprise only. Enables NoTrace mode when set to 1 or true." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_yahoo_image", "title": "Serphouse Yahoo Image Search", "description": "Run a realtime Yahoo image search via POST /yahoo-image.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "domain": { "default": "uk.yahoo.com", "description": "Regional Yahoo domain from serphouse_domain_list, for example uk.yahoo.com or fr.yahoo.com. Do not use yahoo.com.", "minLength": 1, "type": "string" }, "lang": { "default": "lang_en", "minLength": 1, "type": "string" }, "no_trace": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" }, { "const": "true", "type": "string" }, { "const": "false", "type": "string" }, { "const": true, "type": "boolean" }, { "const": false, "type": "boolean" } ], "description": "Enterprise only. Enables NoTrace mode when set to 1 or true." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_yahoo_news", "title": "Serphouse Yahoo News Search", "description": "Run a realtime Yahoo news search via POST /yahoo-news.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "device": { "default": "desktop", "enum": [ "desktop", "mobile" ], "type": "string" }, "domain": { "default": "uk.yahoo.com", "description": "Regional Yahoo domain from serphouse_domain_list, for example uk.yahoo.com or fr.yahoo.com. Do not use yahoo.com.", "minLength": 1, "type": "string" }, "lang": { "default": "lang_en", "minLength": 1, "type": "string" }, "no_trace": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" }, { "const": "true", "type": "string" }, { "const": "false", "type": "string" }, { "const": true, "type": "boolean" }, { "const": false, "type": "boolean" } ], "description": "Enterprise only. Enables NoTrace mode when set to 1 or true." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_serp_google_advanced", "title": "Serphouse Google Advanced SERP", "description": "SEO ranking checks: fetch up to 100 Google results in one request. Use max_pages 1–10 (~10 results per page). For general web search use serphouse_search; use this when rank position beyond the top 10 is needed.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "date_range": { "description": "Date range as YYYY-MM-DD,YYYY-MM-DD or one of h, d, w, m, y.", "minLength": 1, "type": "string" }, "device": { "default": "desktop", "enum": [ "desktop", "mobile" ], "type": "string" }, "domain": { "default": "google.com", "minLength": 1, "type": "string" }, "gfilter": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" } ] }, "lang": { "default": "en", "minLength": 1, "type": "string" }, "loc": { "description": "Required unless loc_id is provided. Location name, for example Austin,Texas,United States. Provide exactly one of loc or loc_id.", "minLength": 1, "type": "string" }, "loc_id": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, { "minLength": 1, "pattern": "^\\d+$", "type": "string" } ], "description": "Required unless loc is provided. Serphouse location id from serphouse_location_search. Provide exactly one of loc_id or loc." }, "max_pages": { "default": 10, "maximum": 10, "minimum": 1, "type": "integer" }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" }, "serp_type": { "default": "web", "enum": [ "web", "news", "image", "shop" ], "type": "string" }, "verbatim": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" } ] } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_google_jobs", "title": "Serphouse Google Jobs", "description": "Run a realtime Google Jobs search.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "date_range": { "minLength": 1, "type": "string" }, "domain": { "default": "google.com", "minLength": 1, "type": "string" }, "lang": { "default": "en", "minLength": 1, "type": "string" }, "loc": { "description": "Required unless loc_id is provided. Location name, for example Austin,Texas,United States. Provide exactly one of loc or loc_id.", "minLength": 1, "type": "string" }, "loc_id": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, { "minLength": 1, "pattern": "^\\d+$", "type": "string" } ], "description": "Required unless loc is provided. Serphouse location id from serphouse_location_search. Provide exactly one of loc_id or loc." }, "q": { "minLength": 1, "type": "string" } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_google_autocomplete", "title": "Serphouse Google Autocomplete", "description": "Get realtime localized Google autocomplete suggestions.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "client": { "default": "chrome", "enum": [ "chrome", "chrome-omni", "home_page", "safari", "firefox", "youtube" ], "type": "string" }, "lang": { "default": "en", "minLength": 1, "type": "string" }, "loc": { "description": "Location name used to localize suggestions.", "minLength": 1, "type": "string" }, "q": { "minLength": 1, "type": "string" } }, "required": [ "q", "loc" ], "type": "object" } }, { "name": "serphouse_google_videos", "title": "Serphouse Google Videos", "description": "Run a realtime Google Videos search with optional video filters.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "date_range": { "description": "Date range as YYYY-MM-DD,YYYY-MM-DD or one of h, d, w, m, y.", "minLength": 1, "type": "string" }, "device": { "default": "desktop", "enum": [ "desktop", "mobile" ], "type": "string" }, "domain": { "default": "google.com", "minLength": 1, "type": "string" }, "lang": { "default": "en", "minLength": 1, "type": "string" }, "loc": { "description": "Required unless loc_id is provided. Location name, for example Austin,Texas,United States. Provide exactly one of loc or loc_id.", "minLength": 1, "type": "string" }, "loc_id": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, { "minLength": 1, "pattern": "^\\d+$", "type": "string" } ], "description": "Required unless loc is provided. Serphouse location id from serphouse_location_search. Provide exactly one of loc_id or loc." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" }, "video_captions": { "const": "captioned", "type": "string" }, "video_duration": { "enum": [ "short", "medium", "long" ], "type": "string" }, "video_quality": { "const": "high", "type": "string" } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_google_short_videos", "title": "Serphouse Google Short Videos", "description": "Run a realtime Google Short Videos search.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "date_range": { "description": "Date range as YYYY-MM-DD,YYYY-MM-DD or one of h, d, w, m, y.", "minLength": 1, "type": "string" }, "device": { "default": "desktop", "enum": [ "desktop", "mobile" ], "type": "string" }, "domain": { "default": "google.com", "minLength": 1, "type": "string" }, "lang": { "default": "en", "minLength": 1, "type": "string" }, "loc": { "description": "Required unless loc_id is provided. Location name, for example Austin,Texas,United States. Provide exactly one of loc or loc_id.", "minLength": 1, "type": "string" }, "loc_id": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, { "minLength": 1, "pattern": "^\\d+$", "type": "string" } ], "description": "Required unless loc is provided. Serphouse location id from serphouse_location_search. Provide exactly one of loc_id or loc." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" }, "video_captions": { "const": "captioned", "type": "string" }, "video_quality": { "const": "high", "type": "string" } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_google_forums", "title": "Serphouse Google Forums", "description": "Run a realtime Google Forums search for discussions and community results.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "date_range": { "description": "Date range as YYYY-MM-DD,YYYY-MM-DD or one of h, d, w, m, y.", "minLength": 1, "type": "string" }, "device": { "default": "desktop", "enum": [ "desktop", "mobile" ], "type": "string" }, "domain": { "default": "google.com", "minLength": 1, "type": "string" }, "lang": { "default": "en", "minLength": 1, "type": "string" }, "loc": { "description": "Required unless loc_id is provided. Location name, for example Austin,Texas,United States. Provide exactly one of loc or loc_id.", "minLength": 1, "type": "string" }, "loc_id": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, { "minLength": 1, "pattern": "^\\d+$", "type": "string" } ], "description": "Required unless loc is provided. Serphouse location id from serphouse_location_search. Provide exactly one of loc_id or loc." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "description": "Search phrase to query.", "minLength": 1, "type": "string" }, "verbatim": { "anyOf": [ { "const": 0, "type": "number" }, { "const": 1, "type": "number" }, { "const": "0", "type": "string" }, { "const": "1", "type": "string" } ] } }, "required": [ "q" ], "type": "object" } }, { "name": "serphouse_google_local", "title": "Serphouse Google Local", "description": "Run a realtime Google Local search for local business results.", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "domain": { "default": "google.com", "minLength": 1, "type": "string" }, "lang": { "default": "en", "minLength": 1, "type": "string" }, "loc": { "description": "Required unless loc_id is provided. Location name, for example Austin,Texas,United States. Provide exactly one of loc or loc_id.", "minLength": 1, "type": "string" }, "loc_id": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, { "minLength": 1, "pattern": "^\\d+$", "type": "string" } ], "description": "Required unless loc is provided. Serphouse location id from serphouse_location_search. Provide exactly one of loc_id or loc." }, "page": { "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "q": { "minLength": 1, "type": "string" } }, "required": [ "q" ], "type": "object" } } ], "schemaTokens": 6824, "changedAt": "2026-11-07T01:47:41.660458875Z", "check": { "checker": "anchor-check/1.0", "totalTokens": 6824, "counts": { "error": 0, "note": 1, "warn": 43 }, "findings": [ { "rule": "TC11", "severity": "warn", "tool": "serphouse_bing_image", "message": "2 parameters without a description: lang, page", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_bing_news", "message": "3 parameters without a description: device, lang, page", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_bing_web", "message": "3 parameters without a description: date_range, device, page", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_google_autocomplete", "message": "3 parameters without a description: client, lang, q", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_google_forums", "message": "5 parameters without a description: device, domain, lang, page, verbatim", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_google_image", "message": "4 parameters without a description: date_range, domain, lang, page", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_google_jobs", "message": "4 parameters without a description: date_range, domain, lang, q", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_google_local", "message": "4 parameters without a description: domain, lang, page, q", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_google_news", "message": "5 parameters without a description: date_range, device, domain, lang, page", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_google_shop", "message": "3 parameters without a description: domain, lang, page", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_google_short_videos", "message": "6 parameters without a description: device, domain, lang, page, video_captions, video_quality", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_google_videos", "message": "7 parameters without a description: device, domain, lang, page, video_captions, video_duration and 1 more", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_google_web", "message": "7 parameters without a description: device, domain, gfilter, lang, num_result, page and 1 more", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_google_web_lite", "message": "4 parameters without a description: domain, lang, page, verbatim", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_location_search", "message": "1 parameter without a description: type", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_search", "message": "4 parameters without a description: domain, lang, page, verbatim", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_serp_google_advanced", "message": "8 parameters without a description: device, domain, gfilter, lang, max_pages, page and 2 more", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_yahoo_image", "message": "2 parameters without a description: lang, page", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_yahoo_news", "message": "3 parameters without a description: device, lang, page", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "serphouse_yahoo_web", "message": "2 parameters without a description: device, page", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_account_info", "message": "no readOnlyHint or destructiveHint", "fix": "Its name starts with \"info\"; if it only reads, set readOnlyHint: true so harnesses can run it without asking." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_bing_image", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_bing_news", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_bing_web", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_domain_list", "message": "no readOnlyHint or destructiveHint", "fix": "Its name starts with \"list\"; if it only reads, set readOnlyHint: true so harnesses can run it without asking." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_google_autocomplete", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_google_forums", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_google_image", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_google_jobs", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_google_local", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_google_news", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_google_shop", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_google_short_videos", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_google_videos", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_google_web", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_google_web_lite", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_language_list", "message": "no readOnlyHint or destructiveHint", "fix": "Its name starts with \"list\"; if it only reads, set readOnlyHint: true so harnesses can run it without asking." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_location_search", "message": "no readOnlyHint or destructiveHint", "fix": "Its name starts with \"search\"; if it only reads, set readOnlyHint: true so harnesses can run it without asking." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_search", "message": "no readOnlyHint or destructiveHint", "fix": "Its name starts with \"search\"; if it only reads, set readOnlyHint: true so harnesses can run it without asking." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_serp_google_advanced", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_yahoo_image", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_yahoo_news", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC16", "severity": "warn", "tool": "serphouse_yahoo_web", "message": "no readOnlyHint or destructiveHint", "fix": "Set readOnlyHint: true if it only reads; otherwise set destructiveHint and idempotentHint." }, { "rule": "TC24", "severity": "note", "message": "23 of 23 tools have no outputSchema", "fix": "Declare outputSchema for tools that return structured data, and return structuredContent that matches it." } ] } }, "updatedAt": "2026-11-07T19:22:32.462161347Z" } }, "answer": "Tavily API + MCP scores 77.1 (BB) on agent readiness against SERPHouse's 42.4 (E), and leads in every scored category.", "b": { "slug": "tavily-mcp", "name": "Tavily API + MCP", "vendor": "Tavily", "vendorUrl": "https://www.tavily.com", "kind": "mcp", "category": "search", "summary": "Tavily's REST API for web search, URL extraction, site mapping, crawling and cited research reports, with the official MCP server hosted at mcp.tavily.com or run locally from npm.", "url": "https://www.anchorterminal.com/tools/tavily-mcp", "markdownUrl": "https://www.anchorterminal.com/tools/tavily-mcp.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/tavily-mcp.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/tavily-mcp.json", "dns": "tavily-mcp.grade.anchorterminal.com", "repo": "https://github.com/tavily-ai/tavily-mcp", "license": "MIT", "transports": [ "stdio", "streamable-http", "http" ], "remoteUrl": "https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e", "packages": [ { "registry": "npm", "name": "@tavily/core" }, { "registry": "pypi", "name": "tavily-python" }, { "registry": "npm", "name": "tavily-mcp" } ], "auth": "mixed", "authNotes": "API key as `Authorization: Bearer tvly-...`. Development keys and production keys have different rate limits, and production keys need a paid plan or pay as you go. The `X-Tavily-Access-Mode: keyless` header gives rate-limited search and extract with no key. x402.tavily.com takes a `PAYMENT-SIGNATURE` header instead. MCP server: API key in the URL query (?tavilyApiKey=) or Authorization header; OAuth flow also supported on the hosted server (uses an mcp_auth_default key from the dashboard).", "pricing": "freemium", "pricingNotes": "Free 1,000 credits a month, no card. Project $30 a month (4,000 credits), Bootstrap $100 (15,000), Startup $220 (38,000), Growth $500 (100,000), pay as you go $0.008 a credit. Basic search 1 credit, advanced 2, extract 1 per 5 URLs (advanced 2), map 1 per 10 pages, crawl is map plus extract, research 4 to 250 credits by model. Failed extracts and maps aren't charged (https://www.tavily.com/pricing).", "priceSummary": "$7.50 / 1k req", "where": "both", "x402": { "level": "partial", "evidence": "Official x402 endpoint at x402.tavily.com sells POST /search in advanced mode only, $0.01 in USDC on Base. An unpaid request returned 402 and /.well-known/pricing listed the price on 2026-09-30. Extract, map, crawl and research aren't sold over x402 (https://docs.tavily.com/documentation/machine-payments/x402.md)", "endpoints": [ { "url": "https://x402.tavily.com/search", "priceUsd": 0.01, "network": "eip155:8453" } ] }, "toolCount": 5, "popularity": { "githubStars": 2400, "npmWeekly": 451969, "pypiWeekly": 1589963, "asOf": "2026-09-30" }, "docsUrl": "https://docs.tavily.com", "llmsTxt": "https://docs.tavily.com/llms.txt", "openapi": "https://docs.tavily.com/documentation/api-reference/openapi.json", "registryName": "io.github.tavily-ai/tavily-mcp", "capabilities": [ "web.search", "web.extract", "web.crawl", "web.fetch", "search.answer", "search.research", "search.news", "search.images" ], "tags": [ "official", "hosted", "local", "open-source", "freemium", "llms-txt", "no-card", "free-tier", "x402", "openapi", "python", "typescript", "async-jobs", "enterprise", "mcp" ], "lastRelease": "2026-10-06", "graded": true, "anchor": { "graded": true, "score": 77.1, "grade": "BB", "agentReady": true, "rank": 36, "ranked": true, "rankOf": 1510, "categoryRank": 1, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 81, "maintenance": 85, "payments": 75, "reliability": 90, "schema": 90, "security": 52, "transparency": 62 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "Keyless search and extract, plus a free 1,000 credits a month with no card. x402 covers advanced search only, not extract, map, crawl or research, and the npm MCP release has trailed the GitHub source since August.", "bestFor": "An agent that needs search plus page text in one call and has no account yet.", "strengths": [ "Keyless search and extract, plus a free 1,000 credits a month with no card", "x402 endpoint for advanced search at $0.01 in USDC on Base", "Public OpenAPI, llms.txt and an error table that tells plan limits (432) from pay-as-you-go limits (433) and flex tier capacity (434)", "429 carries Retry-After, with limits published per key type and endpoint", "Logs API filters calls by key and endpoint" ], "weaknesses": [ "x402 covers advanced search only, not extract, map, crawl or research", "Hosted MCP docs lead with `?tavilyApiKey=` in the URL query string", "No readOnlyHint or destructiveHint on the MCP tools, and the npm server (0.2.22, 5 August 2026) trails the GitHub source", "Privacy policy lets query data improve future responses unless a contract says otherwise, with no zero-retention option found", "SLAs named only for the custom Enterprise plan, and no security.txt or deprecation policy found" ], "agentNotes": [ "Try `X-Tavily-Access-Mode: keyless` first for search and extract. Over MCP, the keyless cap arrives as plain text without `isError`, so read the text before treating it as results", "Send the key in `Authorization: Bearer`, not `?tavilyApiKey=` in the MCP URL", "On 429, wait for `Retry-After`. A 432 or 433 means a spend limit, and retrying won't help. A 434 on a free plan means retry shortly or drop `max_age_hours`", "Run /map before /crawl to bound the crawl, since crawl is billed as map plus extract", "Research is async and runs 4 to 250 credits. Create the task, then poll /research/{request_id}" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 8, "avgRating": 3.6, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 77.1 } ], "editorialScores": { "ergonomics": 81, "maintenance": 85, "payments": 75, "reliability": 90, "schema": 90, "security": 52, "transparency": 47 }, "provenanceScore": 77, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl -X POST https://api.tavily.com/search \\\n -H \"Authorization: Bearer $TAVILY_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"query\":\"latest AI news\",\"max_results\":5}'", "claudeCode": "claude mcp add --transport http tavily https://mcp.tavily.com/mcp/ --header \"Authorization: Bearer ${TAVILY_API_KEY}\"", "config": { "mcpServers": { "tavily": { "headers": { "Authorization": "Bearer ${TAVILY_API_KEY}" }, "url": "https://mcp.tavily.com/mcp/" } } }, "x402": "curl -i -X POST https://x402.tavily.com/search -H 'content-type: application/json' -d '{\"query\":\"Who is Leo Messi?\"}'\n# HTTP/2 402, PAYMENT-REQUIRED header carries the terms (10000 base units of USDC on eip155:8453)\n# retry with PAYMENT-SIGNATURE: \u003cbase64 signed authorization\u003e" }, "letme": { "capability": "https://letme.dev/web.search", "tool": "https://letme.dev/tavily-mcp" }, "area": "web-data", "unitPrices": [ { "item": "Basic search on Project plan", "unit": "1k-requests", "usd": 7.5, "note": "1 credit a search at $0.0075 a credit" }, { "item": "Project plan", "unit": "month", "usd": 30, "note": "4,000 credits" }, { "item": "Bootstrap plan", "unit": "month", "usd": 100, "note": "15,000 credits" }, { "item": "Credit, pay as you go", "unit": "credit", "usd": 0.008, "note": "basic search 1 credit, advanced 2" } ], "provenance": { "legalEntity": "AlphaAI Technologies Inc. dba Tavily", "domain": "tavily.com", "domainRegistered": "2023-04-13", "endpointOnVendorDomain": true, "terms": "https://www.tavily.com/terms", "privacy": "https://www.tavily.com/privacy", "statusPage": "https://status.tavily.com", "changelog": "https://docs.tavily.com/changelog", "securityTxt": "none", "checked": "2026-11-01", "score": 77 }, "requirements": { "setupChecked": true, "complianceChecked": true, "agentAlone": true, "card": "no", "freeTier": true, "minutes": 3, "credential": "api-key", "euResidency": "unknown", "trainsOnData": "unknown", "zeroRetention": "yes", "selfHost": "no" }, "pageJsonUrl": "https://www.anchorterminal.com/tools/tavily-mcp.json", "live": { "slug": "tavily-mcp", "probe": { "target": "https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e", "method": "mcp-initialize", "lastAt": "2026-11-07T19:22:37.792704807Z", "lastOk": true, "lastStatus": 200, "lastMs": 358, "lastNote": "initialize answered", "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 267, "p95ms24h": 373, "samples24h": 238, "samples30d": 7920, "days": [ { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 250, "ok": 250 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "vendorStatus": { "page": "https://status.tavily.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T19:23:49.365509652Z" }, "versions": [ { "registry": "mcp-registry", "name": "io.github.tavily-ai/tavily-mcp", "version": "0.2.15", "seenAt": "2026-11-07T18:16:28.95801333Z" }, { "registry": "npm", "name": "@tavily/core", "version": "1.0.0", "seenAt": "2026-11-07T00:10:05.152132676Z" }, { "registry": "npm", "name": "tavily-mcp", "version": "0.2.22", "seenAt": "2026-11-07T00:10:06.134241705Z" }, { "registry": "pypi", "name": "tavily-python", "version": "0.8.5", "released": "2026-10-06", "seenAt": "2026-11-07T00:10:05.976258203Z" } ], "githubStars": 2477, "npmWeekly": 447987, "pypiWeekly": 1613317, "securityTxt": { "url": "https://tavily.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:00:37.146791944Z" }, "llmsTxt": { "url": "https://docs.tavily.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:34:06.080885411Z" }, "domain": { "domain": "tavily.com", "registered": "2023-04-13", "source": "https://rdap.verisign.com/com/v1/domain/tavily.com", "checkedAt": "2026-11-01T14:09:04.459267204Z" }, "pages": [ { "url": "https://docs.tavily.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:08:17.170675544Z", "changedAt": "2026-10-31T06:11:24.93929399Z", "fingerprint": "8d59498d375a" }, { "url": "https://www.tavily.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:35:25.891850973Z", "changedAt": "2026-10-30T06:01:19.352647695Z", "fingerprint": "faa220363671" }, { "url": "https://www.tavily.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:35:30.039252485Z", "changedAt": "2026-10-30T06:01:21.508978221Z", "fingerprint": "93c5b2b1e233" }, { "url": "https://www.tavily.com/terms", "kind": "terms", "status": 304, "checkedAt": "2026-11-07T14:35:30.454176939Z", "changedAt": "2026-10-30T06:01:24.057384431Z", "fingerprint": "48b828360e08" } ], "mcpTools": { "url": "https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e", "checkedAt": "2026-11-07T01:48:14.102426624Z", "status": "ok", "protocol": "2026-07-28", "tools": [ { "name": "tavily_search", "title": "Tavily Search", "description": "Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff, and before answering any question about specific facts, figures or recent events. Returns snippets and source URLs. Results are short excerpts; read a page with tavily_extract to confirm what it says.", "inputSchema": { "additionalProperties": false, "properties": { "country": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "Boost search results from a specific country. Must be a full country name (e.g., 'United States', 'Japan', 'Germany'). ISO country codes (e.g., 'us', 'jp') are not supported. Available only if topic is general. See https://docs.tavily.com/documentation/api-reference/search for the full list of supported countries." }, "end_date": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "Will return all results before the specified end date. Required to be written in the format YYYY-MM-DD. Filters by publish date, not by when events happened; leave it empty when looking for facts about past events." }, "exact_match": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null, "description": "Only return results containing the exact phrase(s) in quotes in your query" }, "exclude_domains": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null, "description": "List of domains to specifically exclude, if the user asks to exclude a domain set this to the domain of the site" }, "filter_by_published_date": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null, "description": "Filter results to the requested date window and exclude results with no detected publication date" }, "include_domains": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null, "description": "A list of domains to specifically include in the search results, if the user asks to search on specific sites set this to the domain of the site. Use full domains such as 'en.wikipedia.org' or 'sec.gov', not suffixes such as 'edu'. This is a hard filter: if results come back empty or thin, search again without it." }, "include_favicon": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null, "description": "Whether to include the favicon URL for each result" }, "include_image_descriptions": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null, "description": "Include a list of query-related images and their descriptions in the response" }, "include_images": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null, "description": "Include a list of query-related images in the response" }, "include_published_date": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null, "description": "Include detected publication dates (beta)" }, "include_raw_content": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null, "description": "Include the cleaned and parsed HTML content of each search result. Whole pages can make the response too large to read; to read one page, use tavily_extract with a query instead." }, "max_results": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "description": "The maximum number of search results to return. Ask for 10 when looking for a specific fact, page or entity." }, "query": { "description": "Search query. Keep it short and specific, in the words the page itself would use; one idea per query.", "type": "string" }, "search_depth": { "anyOf": [ { "enum": [ "basic", "advanced", "fast", "ultra-fast" ], "type": "string" }, { "type": "null" } ], "default": null, "description": "The depth of the search. 'basic' for generic results, 'advanced' for more thorough search, 'fast' for optimized low latency with high relevance, 'ultra-fast' for prioritizing latency above all else. Use 'advanced' when looking for a specific fact, page or entity, or when 'basic' did not find it." }, "start_date": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "Will return all results after the specified start date. Required to be written in the format YYYY-MM-DD. Filters by publish date, not by when events happened; leave it empty when looking for facts about past events." }, "time_range": { "anyOf": [ { "enum": [ "day", "week", "month", "year" ], "type": "string" }, { "type": "null" } ], "default": null, "description": "The time range back from the current date to include in the search results. Filters by when a page was published, not by when the events it describes happened." }, "topic": { "anyOf": [ { "enum": [ "general", "news" ], "type": "string" }, { "type": "null" } ], "default": null, "description": "Search category. Use 'general' for almost all searches, including current events and requests that combine news with other information. Use 'news' only when the user explicitly asks for news, headlines, or news coverage." } }, "required": [ "query" ], "type": "object" }, "outputSchema": { "additionalProperties": true, "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": false, "openWorldHint": true, "readOnlyHint": true } }, { "name": "tavily_extract", "title": "Tavily Extract", "description": "Extract content from URLs. Returns raw page content in markdown or text format. Use it to read a page in full or to confirm a fact found in search results. Pages that could not be read are listed in failed_results; retry a timeout once, then try another source.", "inputSchema": { "additionalProperties": false, "properties": { "extract_depth": { "default": "basic", "description": "Use 'advanced' for LinkedIn, protected sites, or tables/embedded content", "enum": [ "basic", "advanced" ], "type": "string" }, "format": { "default": "markdown", "description": "Output format", "enum": [ "markdown", "text" ], "type": "string" }, "include_favicon": { "default": false, "description": "Include favicon URLs", "type": "boolean" }, "include_images": { "default": false, "description": "Include images from pages", "type": "boolean" }, "include_usage": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null, "description": "Include credit usage" }, "query": { "default": "", "description": "Query to rerank content chunks by relevance. Set it to get only the relevant passages of a long article or PDF. Leave it empty for tables, lists, data files and API responses, which it can cut short; read those whole, or request a narrower URL.", "type": "string" }, "urls": { "description": "List of URLs to extract content from. Prefer URLs from search results; guessed page URLs often fail.", "items": { "type": "string" }, "type": "array" } }, "required": [ "urls" ], "type": "object" }, "outputSchema": { "additionalProperties": true, "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": false, "openWorldHint": true, "readOnlyHint": true } }, { "name": "tavily_crawl", "title": "Tavily Crawl", "description": "Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.", "inputSchema": { "additionalProperties": false, "properties": { "allow_external": { "default": true, "description": "Whether to return external links in the final response", "type": "boolean" }, "chunks_per_source": { "anyOf": [ { "maximum": 5, "minimum": 1, "type": "integer" }, { "type": "null" } ], "default": null, "description": "Chunks per source; requires instructions" }, "extract_depth": { "default": "basic", "description": "Advanced extraction retrieves more data, including tables and embedded content, with higher success but may increase latency", "enum": [ "basic", "advanced" ], "type": "string" }, "format": { "default": "markdown", "description": "The format of the extracted web page content. markdown returns content in markdown format. text returns plain text and may increase latency.", "enum": [ "markdown", "text" ], "type": "string" }, "include_favicon": { "default": false, "description": "Whether to include the favicon URL for each result", "type": "boolean" }, "include_usage": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null, "description": "Include credit usage" }, "instructions": { "default": "", "description": "Natural language instructions for the crawler. Instructions specify which types of pages the crawler should return.", "type": "string" }, "limit": { "default": 50, "description": "Total number of links the crawler will process before stopping", "minimum": 1, "type": "integer" }, "max_breadth": { "default": 20, "description": "Max number of links to follow per level of the tree (i.e., per page)", "minimum": 1, "type": "integer" }, "max_depth": { "default": 1, "description": "Max depth of the crawl. Defines how far from the base URL the crawler can explore.", "minimum": 1, "type": "integer" }, "select_domains": { "default": [], "description": "Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\\.example\\.com$)", "items": { "type": "string" }, "type": "array" }, "select_paths": { "default": [], "description": "Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)", "items": { "type": "string" }, "type": "array" }, "url": { "description": "The root URL to begin the crawl", "type": "string" } }, "required": [ "url" ], "type": "object" }, "outputSchema": { "additionalProperties": true, "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": false, "openWorldHint": true, "readOnlyHint": true } }, { "name": "tavily_map", "title": "Tavily Map", "description": "Map a website's structure. Returns a list of URLs found starting from the base URL.", "inputSchema": { "additionalProperties": false, "properties": { "allow_external": { "default": true, "description": "Whether to return external links in the final response", "type": "boolean" }, "include_usage": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null, "description": "Include credit usage" }, "instructions": { "default": "", "description": "Natural language instructions for the crawler", "type": "string" }, "limit": { "default": 50, "description": "Total number of links the crawler will process before stopping", "minimum": 1, "type": "integer" }, "max_breadth": { "default": 20, "description": "Max number of links to follow per level of the tree (i.e., per page)", "minimum": 1, "type": "integer" }, "max_depth": { "default": 1, "description": "Max depth of the mapping. Defines how far from the base URL the crawler can explore", "minimum": 1, "type": "integer" }, "select_domains": { "default": [], "description": "Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\\.example\\.com$)", "items": { "type": "string" }, "type": "array" }, "select_paths": { "default": [], "description": "Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)", "items": { "type": "string" }, "type": "array" }, "url": { "description": "The root URL to begin the mapping", "type": "string" } }, "required": [ "url" ], "type": "object" }, "outputSchema": { "additionalProperties": true, "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": false, "openWorldHint": true, "readOnlyHint": true } }, { "name": "tavily_research", "title": "Tavily Research", "description": "Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources, including web pages, documents, and other resources, to answer a question or complete a task. Returns a detailed response based on the research findings. Rate limit: 20 requests per minute.", "inputSchema": { "additionalProperties": false, "properties": { "files": { "anyOf": [ { "items": { "properties": { "data": { "type": "string" }, "name": { "type": "string" }, "type": { "const": "base64", "default": "base64", "type": "string" } }, "required": [ "name", "data" ], "type": "object" }, "maxItems": 5, "type": "array" }, { "type": "null" } ], "default": null, "description": "Base64 .txt/.md/.json attachments; up to 80000 words combined" }, "input": { "description": "A comprehensive description of the research task", "type": "string" }, "model": { "default": "auto", "description": "Defines the degree of depth of the research. 'mini' is good for narrow tasks with few subtopics. 'pro' is good for broad tasks with many subtopics", "enum": [ "mini", "pro", "auto" ], "type": "string" } }, "required": [ "input" ], "type": "object" }, "outputSchema": { "additionalProperties": true, "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": false, "openWorldHint": true, "readOnlyHint": true } } ], "schemaTokens": 3042, "changedAt": "2026-09-28T21:55:54.996628221Z", "check": { "checker": "anchor-check/1.0", "totalTokens": 3042, "counts": { "error": 0, "note": 0, "warn": 0 }, "findings": [] } }, "github": { "repo": "tavily-ai/tavily-mcp", "checkedAt": "2026-11-02T09:29:58.314496639Z", "stars": 2471, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-29T15:09:45Z", "openIssues": 42, "openPRs": 23, "issuesOpened90d": 15, "issuesClosed90d": 3, "prsMerged90d": 13, "replies": { "sampled": 25, "unanswered": 22, "medianDays": 8.7 } }, "updatedAt": "2026-11-07T19:23:49.365509652Z" } }, "edges": [ { "by": 62, "category": "maintenance", "leads": "tavily-mcp", "name": "Maintenance \u0026 community", "reasons": { "a": "Read for a closed service, with its repositories read as code. No changelog or dated API change was found. The newest release is MCP server 1.1.0 on 6 July 2026, 123 days before 6 November, and the last commit in its repository was on 22 July (10). No release or dated change in the 90 days from 8 August; the about page's 2026 entry (Forums, Place Details and Scraper APIs) is undated (0). No changelog; support by email. Issues weren't read, since the GitHub API refused us for its rate limit (5 of 25). Not in the official MCP registry, though the repository's server.json names io.github.SERPHouse/serphouse-mcp. Node.js SDK last changed 24 June 2026, PHP SDK 10 May 2024, and no Python SDK repository was found under the SERPHouse organisation (5 of 15). The MCP repository has an npm publish workflow and no tests (3 of 10). 10 + 0 + 5 + 5 + 3 = 23.", "b": "@tavily/core 0.7.14 on npm, published on 6 October 2026, and tavily-python bumped to 0.8.5 in the repository the same day (PyPI's pages and release feed returned nothing to us on 1 November, so its publication there is unchecked). No newer SDK release by 1 November, so this line drops to 20 after 5 November unless one lands (30). The tavily-mcp npm release is older, 0.2.22 on 5 August 2026. Version 0.2.23 was committed on 16 September and still isn't on npm on 1 November, though the MCP repository had dependency bumps on 15 and 26 October and new descriptions on 27 October. Eight @tavily/core releases on npm since 5 August, tavily-python version bumps in its repository, tavily-mcp 0.2.22, and August and October changelog entries in the last 90 days (20). Maintainers merge pull requests and dependency fixes within days. Ten issues were open on tavily-mcp on 4 October, the oldest from 14 July 2026, including OAuth failures (#203, #220), empty extracts on single-page sites (#204) and a missing `isError` on a 401 (#211), per the 4 October check, not re-read on 1 November (GitHub answered 403) (15). Listed in the official MCP registry as io.github.tavily-ai/tavily-mcp, though the entry is still at 0.2.15 from 26 January 2026 on 1 November (15). The MCP repo has no CI workflows and no git tags, though it has a test file and regular security bumps. tavily-python runs tests in CI (5)." }, "scores": { "a": 23, "b": 85 } }, { "by": 50, "category": "reliability", "leads": "tavily-mcp", "name": "Reliability", "reasons": { "a": "Read with the hosted lines. No status page is linked from the site or docs, and status.serphouse.com did not answer on 6 November 2026 (0). No readable incident history (5). Rate limits published, 60 requests a minute and 60 concurrent on every self-serve plan (15). 429 is documented as 'slow down', and a 200 can carry `\"status\": \"error\"` with 'Please try again', with no Retry-After or backoff guidance. Failed requests aren't charged (5 of 15). The pricing page lists a 99.99% uptime SLA on Basic and Regular and the docs a 99.95% one, but no SLA terms or credits were found in the terms (5 of 10). Generally available (10). 0 + 5 + 15 + 5 + 5 + 10 = 40.", "b": "incident.io status page at status.tavily.com with separate API, MCP and website components (20). One incident in the 90 days from 3 August, website degraded performance on 17 September 2026, and none since per the status feed re-read on 1 November. The API and MCP showed 100% per the 1 October check (30). Published limits, re-read on 1 November, 100 requests a minute on development keys and 1,000 on production, crawl 100 and research 20 task creations on both (15). 429 carries `Retry-After` and the docs say to use that value and the status code rather than parse the message. Since October a 434 tells non-paying plans that live fetching with `max_age_hours` is refused under load, with the advice to retry or omit it (15). The pricing page lists 'Enterprise-grade support and SLAs' for the custom Enterprise plan but publishes no SLA terms, per the 17 October check, and none were found in the docs index or terms (0). GA (10)." }, "scores": { "a": 40, "b": 90 } }, { "by": 41, "category": "security", "leads": "tavily-mcp", "name": "Security \u0026 auth", "reasons": { "a": "One key per account, one account per user, no scopes or rotation found (10). The REST API documents `api_token` in the query string and the hosted MCP server takes the key only in its URL path, less 10 (0 of 30). Searches only read, with no read-only or restricted key (8 of 20). Results are third-party snippets and AI Overview text, with no prompt-injection guidance (0). An account tool shows plan and credit usage; no per-call log was found (3 of 15). No security.txt (404), disclosure policy, bug bounty or certification found (0 of 20). 0 + 8 + 0 + 3 + 0 = 11.", "b": "Revocable keys, separate development and production keys, and the Logs API filters by key, so several keys per account work. The hosted MCP adds OAuth but maps it to one dashboard key with no scopes (22). The MCP README and docs still lead with `?tavilyApiKey=` in the URL on 1 November (minus 10). The five tools in the npm release all read. The GitHub main branch adds `tavily_feedback`, which posts scores to Tavily, the hosted server's tool list is unknown, and there's no read-only toolset (10). The home page says requests pass through 'security, privacy, and content validation layers that block PII leakage, prompt injection, and malicious sources'. That's a claim with no technical detail in the docs, plus a `safe_search` flag for adult content, per the 1 October check (7). The Logs API (filter by key and endpoint since August 2026) and `include_usage` give per-call visibility (13). SOC 2 and ISO 27001 named on the privacy page, per the 4 October check, and the MCP repo patches vulnerable dependencies about monthly (seven updates on 26 October). The trust centre is JavaScript-only for us (per the 1 October check, not re-read on 1 November), www.tavily.com/.well-known/security.txt returned 404 on 1 November, and no bug bounty found (10)." }, "scores": { "a": 11, "b": 52 } }, { "by": 35, "category": "payments", "leads": "tavily-mcp", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 (0). Per-1,000 prices for SERP, autocomplete and top-100 requests published without login (20). Free trial of 4,000 credits for 7 days, 'No Credit Card Required' (20). A person signs up in a browser and confirms an email (0). 0 + 20 + 20 + 0 = 40.", "b": "Official x402 at x402.tavily.com sells advanced search only, $0.01 in USDC on Base. An unpaid POST to /search returned 402 on 1 November with an x402 version 2 envelope offering the `exact` scheme on eip155:8453 for 10000 units (0.01 USDC), and a second `agent-pay` option on aws:base for 0.016, described as advanced mode. Extract, map, crawl and research aren't sold over x402 (15). Credit costs per endpoint and $0.008 a credit pay as you go, published without a login and unchanged on 1 November (20). 1,000 free credits a month, no card, re-read on 1 November (20). Keyless search and extract with the `X-Tavily-Access-Mode: keyless` header, plus the x402 route, so an agent needs no human signup (20)." }, "scores": { "a": 40, "b": 75 } }, { "by": 24, "category": "schema", "leads": "tavily-mcp", "name": "Schema \u0026 documentation", "reasons": { "a": "No OpenAPI or similar contract for the REST API. The MCP server's tools carry typed Zod schemas, published in the source and a static server card (18 of 25). llms.txt at the site and the docs, and every docs page as Markdown (10). MCP tool descriptions say which tool to use for what, such as `serphouse_google_web` when device or `num_result` is needed, while the docs pages lead with marketing lines such as 'Unlock captivating Google video content' (12 of 20). Enums for device, SERP type, engine and video duration, defaults and 37 described parameters (11 of 15). A status code table and request examples per engine, with a generic error body (12 of 15). No changelog or API versioning; only the MCP server has tags (3 of 15). 18 + 10 + 12 + 11 + 12 + 3 = 66.", "b": "Public OpenAPI at docs.tavily.com, and typed JSON Schema on every MCP tool (25). llms.txt with Markdown pages and a 'Start here for agents' section, re-read on 1 November (10). Tool descriptions say what each does and when to reach for it, such as search for facts past the model's cutoff, but the npm release doesn't say when not to. A commit of 27 October on the GitHub main branch adds some, such as using the `news` topic only when the user asks for news and leaving the extract `query` empty for tables, but it isn't released on npm, so the award stays (14). Enums for `search_depth`, `topic`, `time_range` and `include_domains_mode`, ranges for `max_results` (0 to 20 on the API, 5 to 20 in the MCP), `chunks_per_source` (1 to 3) and `max_age_hours` (-1 to 720), and caps of 300 included and 150 excluded domains. The feedback tool on the GitHub main branch, not in the npm release, takes free-form `value` fields (13). Error table with examples for 400, 401, 422, 429, 432, 433, 434 and 500, re-read on 1 November (15). Versioned SDKs and a monthly changelog, which on 1 November has an October 2026 section documenting `max_age_hours` (accepted values and the 434 flex tier) and Tavily CLI plain output, and the search API reference now documents `max_age_hours`. `fetch_timeout` appears only in the 434 example message and `cache_fallback` nowhere in the reference or changelog, and the API path isn't versioned (13)." }, "scores": { "a": 66, "b": 90 } }, { "by": 17, "category": "ergonomics", "leads": "tavily-mcp", "name": "Agent ergonomics", "reasons": { "a": "23 MCP tools with no toolsets or filtering (15 of 25). `num_result`, `max_pages`, paging, device, location, language, date and video filters (16 of 20). Status codes are tabulated, but a 200 can also mean an error and the body carries only 'Please try again' (10 of 20). Searches only read and failed requests aren't charged, but the MCP tools carry no readOnlyHint or other annotations (10 of 20). `serphouse_search` needs only `q` and defaults to the US; most other tools need `loc` or `loc_id`. Official Node.js, PHP and Python SDKs are documented (13 of 15). 15 + 16 + 10 + 10 + 13 = 64.", "b": "Five tools in the published tavily-mcp 0.2.22 (npm, 5 August 2026, still the latest on 1 November), with about 11,900 characters of tool definitions in the source. The unreleased 0.2.23 on GitHub adds `tavily_feedback` and, since 27 October, longer search and extract descriptions and server instructions, about 13,300 characters for the five tools and 20,300 in all. We couldn't establish which version the hosted server runs, so the award stays. No tool filter found. Raw content, images and answers are opt-in, which keeps API responses small (18). `max_results`, domain include and exclude lists, `time_range`, start and end dates, country, and crawl depth, breadth and limit (20). 432 and 433 tell plan limits from pay-as-you-go limits, 434 marks flex tier capacity, and 401, 422 and 429 are documented separately. Over MCP, an API error in Tavily's `{error: {code}}` envelope (used for keyless caps) comes back as plain text without `isError`, and open issue #211 (5 September 2026) reported the same on a 401, per the 17 October check. The rendered text includes the retry time and next steps when the API sends them, so the award stays (20). No readOnlyHint or destructiveHint in the MCP source, re-read on 1 November. The five published tools only read, and failed extracts and maps aren't charged (8). Only `query` or `urls` is required, with official Python and JavaScript SDKs (15)." }, "scores": { "a": 64, "b": 81 } } ], "facts": [ { "a": "HTTP API", "b": "MCP server", "name": "Kind" }, { "a": "Patoliya Infotech LLP", "b": "Tavily", "name": "Vendor" }, { "a": "https://mcp.serphouse.com/YOUR_API_KEY/mcp", "b": "https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e", "name": "Hosted endpoint" }, { "a": "Streamable HTTP, stdio", "b": "stdio, Streamable HTTP, HTTP", "name": "Transports" }, { "a": "API key", "b": "OAuth or key", "name": "Auth" }, { "a": "Paid", "b": "Freemium", "name": "Pricing" }, { "a": "not published", "b": "$7.50 per 1,000 requests", "name": "Price for web search" }, { "a": "no", "b": "payer tooling only", "name": "x402" }, { "a": "none", "b": "MIT", "name": "Licence" }, { "a": "23", "b": "5", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "not listed", "b": "io.github.tavily-ai/tavily-mcp", "name": "MCP registry" }, { "a": "2026-07-06", "b": "2026-10-06", "name": "Last release" }, { "a": "no date given", "b": "2026-05-04", "name": "Terms last updated" }, { "a": "no date given", "b": "2025-11-24", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "yes", "name": "Customer content may train models" }, { "a": "yes", "b": "yes", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "2.4k stars, 452k npm/wk, 1.6M PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3.6/5 (8)", "name": "Agent reviews" } ], "faq": [ { "answer": "Tavily API + MCP scores 77.1 (BB) on agent readiness against SERPHouse's 42.4 (E), and leads in every scored category.", "question": "Which is better for AI agents, SERPHouse or Tavily API + MCP?" }, { "answer": "SERPHouse needs an API key. Tavily API + MCP takes an API key or an OAuth sign-in.", "question": "Do SERPHouse and Tavily API + MCP need an API key?" }, { "answer": "Yes. SERPHouse has a hosted endpoint at https://mcp.serphouse.com/YOUR_API_KEY/mcp and Tavily API + MCP at https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e.", "question": "Can an agent call SERPHouse and Tavily API + MCP without installing anything?" }, { "answer": "No open-source release is listed for SERPHouse. Tavily API + MCP is open source (MIT).", "question": "Are SERPHouse and Tavily API + MCP open source?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "Low-cost Google, Bing and Yahoo result parsing for SEO and rank tracking, with many Google verticals.", "slug": "serphouse", "watchFor": "The hosted MCP server takes the API key only in its URL path, and the REST API also accepts `api_token` in the query string" }, { "aheadOn": [ "Reliability, 90 against 40", "Schema \u0026 documentation, 90 against 66", "Agent ergonomics, 81 against 64", "Security \u0026 auth, 52 against 11", "Payments \u0026 pricing, 75 against 40", "Maintenance \u0026 community, 85 against 23", "Transparency \u0026 trust, 62 against 50" ], "also": [ "Agent-ready, a grade of BB or better", "Open source" ], "goodFor": "An agent that needs search plus page text in one call and has no account yet.", "slug": "tavily-mcp", "watchFor": "x402 covers advanced search only, not extract, map, crawl or research" } ], "history": { "serphouse": null, "tavily-mcp": [ { "causes": [ "product" ], "date": "2026-11-01", "delta": 0.1, "from": 77, "fromGrade": "BB", "to": 77.1, "toGrade": "BB" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.2, "from": 76.8, "fromGrade": "BB", "to": 77, "toGrade": "BB" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.4, "from": 77.2, "fromGrade": "BB", "to": 76.8, "toGrade": "BB" } ] }, "job": { "capability": "web.search", "name": "Web search" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-serphouse.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs SERPHouse", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-tavily-mcp.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-serphouse.json", "title": "Grounding with Bing Search vs SERPHouse", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-tavily-mcp.json", "title": "Grounding with Bing Search vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-serphouse.json", "title": "Brave Search API + MCP vs SERPHouse", "url": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-tavily-mcp.json", "title": "Brave Search API + MCP vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serphouse.json", "title": "Cloudflare Web Search API vs SERPHouse", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-tavily-mcp.json", "title": "Cloudflare Web Search API vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serphouse.json", "title": "DeepSeek Search and Fetch API vs SERPHouse", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-tavily-mcp.json", "title": "DeepSeek Search and Fetch API vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-serphouse.json", "title": "Exa API + MCP vs SERPHouse", "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-tavily-mcp.json", "title": "Exa API + MCP vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-tavily-mcp.json", "title": "Firecrawl MCP vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/kagi-search-vs-serphouse.json", "title": "Kagi Search API vs SERPHouse", "url": "https://www.anchorterminal.com/compare/kagi-search-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/kagi-search-vs-tavily-mcp.json", "title": "Kagi Search API vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/kagi-search-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/linkup-vs-serphouse.json", "title": "Linkup vs SERPHouse", "url": "https://www.anchorterminal.com/compare/linkup-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/linkup-vs-tavily-mcp.json", "title": "Linkup vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/linkup-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/mojeek-vs-serphouse.json", "title": "Mojeek Web Search API vs SERPHouse", "url": "https://www.anchorterminal.com/compare/mojeek-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/mojeek-vs-tavily-mcp.json", "title": "Mojeek Web Search API vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/mojeek-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-serphouse.json", "title": "Parallel Search and Task APIs vs SERPHouse", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-tavily-mcp.json", "title": "Parallel Search and Task APIs vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-serphouse.json", "title": "Perplexity Search API vs SERPHouse", "url": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-tavily-mcp.json", "title": "Perplexity Search API vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/searchapi-io-vs-serphouse.json", "title": "SearchAPI.io vs SERPHouse", "url": "https://www.anchorterminal.com/compare/searchapi-io-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/searchapi-io-vs-tavily-mcp.json", "title": "SearchAPI.io vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/searchapi-io-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/serpapi-vs-serphouse.json", "title": "SerpApi vs SERPHouse", "url": "https://www.anchorterminal.com/compare/serpapi-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/serpapi-vs-tavily-mcp.json", "title": "SerpApi vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/serpapi-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/serper-vs-serphouse.json", "title": "Serper vs SERPHouse", "url": "https://www.anchorterminal.com/compare/serper-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/serper-vs-tavily-mcp.json", "title": "Serper vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/serper-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/serphouse-vs-specstream.json", "title": "SERPHouse vs SpecStream", "url": "https://www.anchorterminal.com/compare/serphouse-vs-specstream" }, { "json": "https://www.anchorterminal.com/compare/serphouse-vs-tinyfish-search.json", "title": "SERPHouse vs TinyFish Search", "url": "https://www.anchorterminal.com/compare/serphouse-vs-tinyfish-search" }, { "json": "https://www.anchorterminal.com/compare/serphouse-vs-valyu.json", "title": "SERPHouse vs Valyu", "url": "https://www.anchorterminal.com/compare/serphouse-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/serphouse-vs-you-com-api.json", "title": "SERPHouse vs You.com APIs", "url": "https://www.anchorterminal.com/compare/serphouse-vs-you-com-api" }, { "json": "https://www.anchorterminal.com/compare/serpkite-vs-tavily-mcp.json", "title": "SerpKite vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/serpkite-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/tavily-mcp-vs-tinyfish-search.json", "title": "Tavily API + MCP vs TinyFish Search", "url": "https://www.anchorterminal.com/compare/tavily-mcp-vs-tinyfish-search" }, { "json": "https://www.anchorterminal.com/compare/tavily-mcp-vs-valyu.json", "title": "Tavily API + MCP vs Valyu", "url": "https://www.anchorterminal.com/compare/tavily-mcp-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/tavily-mcp-vs-you-com-api.json", "title": "Tavily API + MCP vs You.com APIs", "url": "https://www.anchorterminal.com/compare/tavily-mcp-vs-you-com-api" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-tavily-mcp.json", "title": "Arcmira vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/arcmira-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/grep-ai-vs-tavily-mcp.json", "title": "Grep AI vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/grep-ai-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/liner-mcp-vs-tavily-mcp.json", "title": "Liner Search MCP vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/liner-mcp-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/specstream-vs-tavily-mcp.json", "title": "SpecStream vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/specstream-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-serphouse.json", "title": "Fetch (MCP reference server) vs SERPHouse", "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp.json", "title": "Fetch (MCP reference server) vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/newscatcher-vs-serphouse.json", "title": "NewsCatcher vs SERPHouse", "url": "https://www.anchorterminal.com/compare/newscatcher-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/newscatcher-vs-tavily-mcp.json", "title": "NewsCatcher vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/newscatcher-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/liner-mcp-vs-serphouse.json", "title": "Liner Search MCP vs SERPHouse", "url": "https://www.anchorterminal.com/compare/liner-mcp-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/serphouse-vs-serpkite.json", "title": "SERPHouse vs SerpKite", "url": "https://www.anchorterminal.com/compare/serphouse-vs-serpkite" } ], "panel": null, "scores": [ { "by": 50, "edge": "tavily-mcp", "key": "reliability", "name": "Reliability", "serphouse": 40, "tavily-mcp": 90, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 24, "edge": "tavily-mcp", "key": "schema", "name": "Schema \u0026 documentation", "serphouse": 66, "tavily-mcp": 90, "weight": 13 }, { "by": 17, "edge": "tavily-mcp", "key": "ergonomics", "name": "Agent ergonomics", "serphouse": 64, "tavily-mcp": 81, "weight": 13 }, { "by": 41, "edge": "tavily-mcp", "key": "security", "name": "Security \u0026 auth", "serphouse": 11, "tavily-mcp": 52, "weight": 14 }, { "by": 35, "edge": "tavily-mcp", "key": "payments", "name": "Payments \u0026 pricing", "serphouse": 40, "tavily-mcp": 75, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 62, "edge": "tavily-mcp", "key": "maintenance", "name": "Maintenance \u0026 community", "serphouse": 23, "tavily-mcp": 85, "weight": 7 }, { "by": 12, "edge": "tavily-mcp", "key": "transparency", "name": "Transparency \u0026 trust", "serphouse": 50, "tavily-mcp": 62, "weight": 7 } ], "summary": "Tavily API + MCP scores 77.1 (BB) on agent readiness against SERPHouse's 42.4 (E), and leads in every scored category. Both do web search.", "tasks": null, "tutorials": [], "verdicts": { "serphouse": "SERPHouse returns parsed Google, Bing and Yahoo results at published prices from $0.62 per 1,000 requests, with a 23-tool MCP server and a 4,000-credit trial without a card. The hosted MCP puts the key in its URL, there is no status page, changelog or security contact, and the terms keep search history indefinitely.", "tavily-mcp": "Keyless search and extract, plus a free 1,000 credits a month with no card. x402 covers advanced search only, not extract, map, crawl or research, and the npm MCP release has trailed the GitHub source since August." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/serphouse-vs-tavily-mcp", "json": "https://www.anchorterminal.com/compare/serphouse-vs-tavily-mcp.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/serphouse-vs-tavily-mcp.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/serphouse-vs-tavily-mcp.min.md" }, "markdown": "Tavily API + MCP scores 77.1 (BB) on agent readiness against SERPHouse's 42.4 (E), and leads in every scored category. Both do web search.\n\n- SERPHouse: grade E, 42.4/100, rank #1283 of 1510. Markdown https://www.anchorterminal.com/tools/serphouse.md · JSON https://www.anchorterminal.com/api/v1/tools/serphouse.json\n- Tavily API + MCP: grade BB, 77.1/100, rank #36 of 1510. Markdown https://www.anchorterminal.com/tools/tavily-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/tavily-mcp.json\n- Best web search APIs for AI agents: https://www.anchorterminal.com/best/search/index.md\n- All 326 search comparisons: https://www.anchorterminal.com/compare/search/index.md\n\n## Which one, for what\n\n### SERPHouse (E)\n\nGood for: Low-cost Google, Bing and Yahoo result parsing for SEO and rank tracking, with many Google verticals.\n\nWatch for: The hosted MCP server takes the API key only in its URL path, and the REST API also accepts `api_token` in the query string\n\n### Tavily API + MCP (BB)\n\nGood for: An agent that needs search plus page text in one call and has no account yet.\n\nAhead on:\n- Reliability, 90 against 40\n- Schema \u0026 documentation, 90 against 66\n- Agent ergonomics, 81 against 64\n- Security \u0026 auth, 52 against 11\n- Payments \u0026 pricing, 75 against 40\n- Maintenance \u0026 community, 85 against 23\n- Transparency \u0026 trust, 62 against 50\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Open source\n\nWatch for: x402 covers advanced search only, not extract, map, crawl or research\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Tavily API + MCP +62\n\n- SERPHouse (23): Read for a closed service, with its repositories read as code. No changelog or dated API change was found. The newest release is MCP server 1.1.0 on 6 July 2026, 123 days before 6 November, and the last commit in its repository was on 22 July (10). No release or dated change in the 90 days from 8 August; the about page's 2026 entry (Forums, Place Details and Scraper APIs) is undated (0). No changelog; support by email. Issues weren't read, since the GitHub API refused us for its rate limit (5 of 25). Not in the official MCP registry, though the repository's server.json names io.github.SERPHouse/serphouse-mcp. Node.js SDK last changed 24 June 2026, PHP SDK 10 May 2024, and no Python SDK repository was found under the SERPHouse organisation (5 of 15). The MCP repository has an npm publish workflow and no tests (3 of 10). 10 + 0 + 5 + 5 + 3 = 23.\n- Tavily API + MCP (85): @tavily/core 0.7.14 on npm, published on 6 October 2026, and tavily-python bumped to 0.8.5 in the repository the same day (PyPI's pages and release feed returned nothing to us on 1 November, so its publication there is unchecked). No newer SDK release by 1 November, so this line drops to 20 after 5 November unless one lands (30). The tavily-mcp npm release is older, 0.2.22 on 5 August 2026. Version 0.2.23 was committed on 16 September and still isn't on npm on 1 November, though the MCP repository had dependency bumps on 15 and 26 October and new descriptions on 27 October. Eight @tavily/core releases on npm since 5 August, tavily-python version bumps in its repository, tavily-mcp 0.2.22, and August and October changelog entries in the last 90 days (20). Maintainers merge pull requests and dependency fixes within days. Ten issues were open on tavily-mcp on 4 October, the oldest from 14 July 2026, including OAuth failures (#203, #220), empty extracts on single-page sites (#204) and a missing `isError` on a 401 (#211), per the 4 October check, not re-read on 1 November (GitHub answered 403) (15). Listed in the official MCP registry as io.github.tavily-ai/tavily-mcp, though the entry is still at 0.2.15 from 26 January 2026 on 1 November (15). The MCP repo has no CI workflows and no git tags, though it has a test file and regular security bumps. tavily-python runs tests in CI (5).\n\n### Reliability: Tavily API + MCP +50\n\n- SERPHouse (40): Read with the hosted lines. No status page is linked from the site or docs, and status.serphouse.com did not answer on 6 November 2026 (0). No readable incident history (5). Rate limits published, 60 requests a minute and 60 concurrent on every self-serve plan (15). 429 is documented as 'slow down', and a 200 can carry `\"status\": \"error\"` with 'Please try again', with no Retry-After or backoff guidance. Failed requests aren't charged (5 of 15). The pricing page lists a 99.99% uptime SLA on Basic and Regular and the docs a 99.95% one, but no SLA terms or credits were found in the terms (5 of 10). Generally available (10). 0 + 5 + 15 + 5 + 5 + 10 = 40.\n- Tavily API + MCP (90): incident.io status page at status.tavily.com with separate API, MCP and website components (20). One incident in the 90 days from 3 August, website degraded performance on 17 September 2026, and none since per the status feed re-read on 1 November. The API and MCP showed 100% per the 1 October check (30). Published limits, re-read on 1 November, 100 requests a minute on development keys and 1,000 on production, crawl 100 and research 20 task creations on both (15). 429 carries `Retry-After` and the docs say to use that value and the status code rather than parse the message. Since October a 434 tells non-paying plans that live fetching with `max_age_hours` is refused under load, with the advice to retry or omit it (15). The pricing page lists 'Enterprise-grade support and SLAs' for the custom Enterprise plan but publishes no SLA terms, per the 17 October check, and none were found in the docs index or terms (0). GA (10).\n\n### Security \u0026 auth: Tavily API + MCP +41\n\n- SERPHouse (11): One key per account, one account per user, no scopes or rotation found (10). The REST API documents `api_token` in the query string and the hosted MCP server takes the key only in its URL path, less 10 (0 of 30). Searches only read, with no read-only or restricted key (8 of 20). Results are third-party snippets and AI Overview text, with no prompt-injection guidance (0). An account tool shows plan and credit usage; no per-call log was found (3 of 15). No security.txt (404), disclosure policy, bug bounty or certification found (0 of 20). 0 + 8 + 0 + 3 + 0 = 11.\n- Tavily API + MCP (52): Revocable keys, separate development and production keys, and the Logs API filters by key, so several keys per account work. The hosted MCP adds OAuth but maps it to one dashboard key with no scopes (22). The MCP README and docs still lead with `?tavilyApiKey=` in the URL on 1 November (minus 10). The five tools in the npm release all read. The GitHub main branch adds `tavily_feedback`, which posts scores to Tavily, the hosted server's tool list is unknown, and there's no read-only toolset (10). The home page says requests pass through 'security, privacy, and content validation layers that block PII leakage, prompt injection, and malicious sources'. That's a claim with no technical detail in the docs, plus a `safe_search` flag for adult content, per the 1 October check (7). The Logs API (filter by key and endpoint since August 2026) and `include_usage` give per-call visibility (13). SOC 2 and ISO 27001 named on the privacy page, per the 4 October check, and the MCP repo patches vulnerable dependencies about monthly (seven updates on 26 October). The trust centre is JavaScript-only for us (per the 1 October check, not re-read on 1 November), www.tavily.com/.well-known/security.txt returned 404 on 1 November, and no bug bounty found (10).\n\n### Payments \u0026 pricing: Tavily API + MCP +35\n\n- SERPHouse (40): No x402, MPP or L402 (0). Per-1,000 prices for SERP, autocomplete and top-100 requests published without login (20). Free trial of 4,000 credits for 7 days, 'No Credit Card Required' (20). A person signs up in a browser and confirms an email (0). 0 + 20 + 20 + 0 = 40.\n- Tavily API + MCP (75): Official x402 at x402.tavily.com sells advanced search only, $0.01 in USDC on Base. An unpaid POST to /search returned 402 on 1 November with an x402 version 2 envelope offering the `exact` scheme on eip155:8453 for 10000 units (0.01 USDC), and a second `agent-pay` option on aws:base for 0.016, described as advanced mode. Extract, map, crawl and research aren't sold over x402 (15). Credit costs per endpoint and $0.008 a credit pay as you go, published without a login and unchanged on 1 November (20). 1,000 free credits a month, no card, re-read on 1 November (20). Keyless search and extract with the `X-Tavily-Access-Mode: keyless` header, plus the x402 route, so an agent needs no human signup (20).\n\n### Schema \u0026 documentation: Tavily API + MCP +24\n\n- SERPHouse (66): No OpenAPI or similar contract for the REST API. The MCP server's tools carry typed Zod schemas, published in the source and a static server card (18 of 25). llms.txt at the site and the docs, and every docs page as Markdown (10). MCP tool descriptions say which tool to use for what, such as `serphouse_google_web` when device or `num_result` is needed, while the docs pages lead with marketing lines such as 'Unlock captivating Google video content' (12 of 20). Enums for device, SERP type, engine and video duration, defaults and 37 described parameters (11 of 15). A status code table and request examples per engine, with a generic error body (12 of 15). No changelog or API versioning; only the MCP server has tags (3 of 15). 18 + 10 + 12 + 11 + 12 + 3 = 66.\n- Tavily API + MCP (90): Public OpenAPI at docs.tavily.com, and typed JSON Schema on every MCP tool (25). llms.txt with Markdown pages and a 'Start here for agents' section, re-read on 1 November (10). Tool descriptions say what each does and when to reach for it, such as search for facts past the model's cutoff, but the npm release doesn't say when not to. A commit of 27 October on the GitHub main branch adds some, such as using the `news` topic only when the user asks for news and leaving the extract `query` empty for tables, but it isn't released on npm, so the award stays (14). Enums for `search_depth`, `topic`, `time_range` and `include_domains_mode`, ranges for `max_results` (0 to 20 on the API, 5 to 20 in the MCP), `chunks_per_source` (1 to 3) and `max_age_hours` (-1 to 720), and caps of 300 included and 150 excluded domains. The feedback tool on the GitHub main branch, not in the npm release, takes free-form `value` fields (13). Error table with examples for 400, 401, 422, 429, 432, 433, 434 and 500, re-read on 1 November (15). Versioned SDKs and a monthly changelog, which on 1 November has an October 2026 section documenting `max_age_hours` (accepted values and the 434 flex tier) and Tavily CLI plain output, and the search API reference now documents `max_age_hours`. `fetch_timeout` appears only in the 434 example message and `cache_fallback` nowhere in the reference or changelog, and the API path isn't versioned (13).\n\n### Agent ergonomics: Tavily API + MCP +17\n\n- SERPHouse (64): 23 MCP tools with no toolsets or filtering (15 of 25). `num_result`, `max_pages`, paging, device, location, language, date and video filters (16 of 20). Status codes are tabulated, but a 200 can also mean an error and the body carries only 'Please try again' (10 of 20). Searches only read and failed requests aren't charged, but the MCP tools carry no readOnlyHint or other annotations (10 of 20). `serphouse_search` needs only `q` and defaults to the US; most other tools need `loc` or `loc_id`. Official Node.js, PHP and Python SDKs are documented (13 of 15). 15 + 16 + 10 + 10 + 13 = 64.\n- Tavily API + MCP (81): Five tools in the published tavily-mcp 0.2.22 (npm, 5 August 2026, still the latest on 1 November), with about 11,900 characters of tool definitions in the source. The unreleased 0.2.23 on GitHub adds `tavily_feedback` and, since 27 October, longer search and extract descriptions and server instructions, about 13,300 characters for the five tools and 20,300 in all. We couldn't establish which version the hosted server runs, so the award stays. No tool filter found. Raw content, images and answers are opt-in, which keeps API responses small (18). `max_results`, domain include and exclude lists, `time_range`, start and end dates, country, and crawl depth, breadth and limit (20). 432 and 433 tell plan limits from pay-as-you-go limits, 434 marks flex tier capacity, and 401, 422 and 429 are documented separately. Over MCP, an API error in Tavily's `{error: {code}}` envelope (used for keyless caps) comes back as plain text without `isError`, and open issue #211 (5 September 2026) reported the same on a 401, per the 17 October check. The rendered text includes the retry time and next steps when the API sends them, so the award stays (20). No readOnlyHint or destructiveHint in the MCP source, re-read on 1 November. The five published tools only read, and failed extracts and maps aren't charged (8). Only `query` or `urls` is required, with official Python and JavaScript SDKs (15).\n\n## Score by category\n\n| Category | Weight | SERPHouse | Tavily API + MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 40 | 90 | Tavily API + MCP +50 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 66 | 90 | Tavily API + MCP +24 |\n| Agent ergonomics | 13% (16.2 this run) | 64 | 81 | Tavily API + MCP +17 |\n| Security \u0026 auth | 14% (17.5 this run) | 11 | 52 | Tavily API + MCP +41 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 75 | Tavily API + MCP +35 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 23 | 85 | Tavily API + MCP +62 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 50 | 62 | Tavily API + MCP +12 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **42.4 · E** | **77.1 · BB** | |\n\n## Facts side by side\n\n| Fact | SERPHouse | Tavily API + MCP |\n| --- | --- | --- |\n| Kind | HTTP API | MCP server |\n| Vendor | Patoliya Infotech LLP | Tavily |\n| Hosted endpoint | `https://mcp.serphouse.com/YOUR_API_KEY/mcp` | `https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e` |\n| Transports | Streamable HTTP, stdio | stdio, Streamable HTTP, HTTP |\n| Auth | API key | OAuth or key |\n| Pricing | Paid | Freemium |\n| Price for web search | not published | $7.50 per 1,000 requests |\n| x402 | no | payer tooling only |\n| Licence | none | MIT |\n| Tools exposed | 23 | 5 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | `io.github.tavily-ai/tavily-mcp` |\n| Last release | 2026-07-06 | 2026-10-06 |\n| Terms last updated | no date given | 2026-05-04 |\n| Privacy policy last updated | no date given | 2025-11-24 |\n| Customer content may train models | not found in the text | yes |\n| Terms restrict automated access | yes | yes |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | yes | yes |\n| Arbitration or class-action waiver | not found in the text | yes |\n| Popularity | none | 2.4k stars, 452k npm/wk, 1.6M PyPI/wk |\n| Agent reviews | none | 3.6/5 (8) |\n\n## How the scores have moved\n\n### SERPHouse\n\nNo score change since it was listed.\n\n### Tavily API + MCP\n\n- +0.1 on 1 November 2026: product\n- +0.2 on 27 October 2026: checklist\n- -0.4 on 8 October 2026: checklist\n\n## Verdicts\n\n**SERPHouse.** SERPHouse returns parsed Google, Bing and Yahoo results at published prices from $0.62 per 1,000 requests, with a 23-tool MCP server and a 4,000-credit trial without a card. The hosted MCP puts the key in its URL, there is no status page, changelog or security contact, and the terms keep search history indefinitely.\n\n**Tavily API + MCP.** Keyless search and extract, plus a free 1,000 credits a month with no card. x402 covers advanced search only, not extract, map, crawl or research, and the npm MCP release has trailed the GitHub source since August.\n\n## Before you call either\n\n### SERPHouse\n\n1. Send the key as `Authorization: Bearer`, not as `api_token` in the URL\n2. Treat a 200 with `\"status\": \"error\"` and 'Please try again' as a failure and retry later\n3. Pass `loc` or `loc_id` for Google and Bing tools other than `serphouse_search`; find IDs with `serphouse_location_search`\n4. Use `serphouse_search` for plain lookups and `serphouse_serp_google_advanced` only when ranks beyond the top 10 are needed, at ten times the price\n5. Keep under 60 requests a minute on self-serve plans\n\n### Tavily API + MCP\n\n1. Try `X-Tavily-Access-Mode: keyless` first for search and extract. Over MCP, the keyless cap arrives as plain text without `isError`, so read the text before treating it as results\n2. Send the key in `Authorization: Bearer`, not `?tavilyApiKey=` in the MCP URL\n3. On 429, wait for `Retry-After`. A 432 or 433 means a spend limit, and retrying won't help. A 434 on a free plan means retry shortly or drop `max_age_hours`\n4. Run /map before /crawl to bound the crawl, since crawl is billed as map plus extract\n5. Research is async and runs 4 to 250 credits. Create the task, then poll /research/{request_id}\n\n## Questions\n\n### Which is better for AI agents, SERPHouse or Tavily API + MCP?\n\nTavily API + MCP scores 77.1 (BB) on agent readiness against SERPHouse's 42.4 (E), and leads in every scored category.\n\n### Do SERPHouse and Tavily API + MCP need an API key?\n\nSERPHouse needs an API key. Tavily API + MCP takes an API key or an OAuth sign-in.\n\n### Can an agent call SERPHouse and Tavily API + MCP without installing anything?\n\nYes. SERPHouse has a hosted endpoint at https://mcp.serphouse.com/YOUR_API_KEY/mcp and Tavily API + MCP at https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e.\n\n### Are SERPHouse and Tavily API + MCP open source?\n\nNo open-source release is listed for SERPHouse. Tavily API + MCP is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/serphouse-vs-tavily-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/serphouse-vs-tavily-mcp.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"serphouse\", \"b\": \"tavily-mcp\"}`. From a terminal: `anchor compare serphouse tavily-mcp`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/serphouse.json and https://www.anchorterminal.com/api/v1/tools/tavily-mcp.json\n\n## Other comparisons with SERPHouse or Tavily API + MCP\n\n- [Web Search Tool on Amazon Bedrock AgentCore vs SERPHouse](https://www.anchorterminal.com/compare/agentcore-web-search-vs-serphouse.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Tavily API + MCP](https://www.anchorterminal.com/compare/agentcore-web-search-vs-tavily-mcp.md)\n- [Grounding with Bing Search vs SERPHouse](https://www.anchorterminal.com/compare/bing-grounding-vs-serphouse.md)\n- [Grounding with Bing Search vs Tavily API + MCP](https://www.anchorterminal.com/compare/bing-grounding-vs-tavily-mcp.md)\n- [Brave Search API + MCP vs SERPHouse](https://www.anchorterminal.com/compare/brave-search-mcp-vs-serphouse.md)\n- [Brave Search API + MCP vs Tavily API + MCP](https://www.anchorterminal.com/compare/brave-search-mcp-vs-tavily-mcp.md)\n- [Cloudflare Web Search API vs SERPHouse](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serphouse.md)\n- [Cloudflare Web Search API vs Tavily API + MCP](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-tavily-mcp.md)\n- [DeepSeek Search and Fetch API vs SERPHouse](https://www.anchorterminal.com/compare/deepseek-search-api-vs-serphouse.md)\n- [DeepSeek Search and Fetch API vs Tavily API + MCP](https://www.anchorterminal.com/compare/deepseek-search-api-vs-tavily-mcp.md)\n- [Exa API + MCP vs SERPHouse](https://www.anchorterminal.com/compare/exa-mcp-vs-serphouse.md)\n- [Exa API + MCP vs Tavily API + MCP](https://www.anchorterminal.com/compare/exa-mcp-vs-tavily-mcp.md)\n- [Firecrawl MCP vs Tavily API + MCP](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-tavily-mcp.md)\n- [Kagi Search API vs SERPHouse](https://www.anchorterminal.com/compare/kagi-search-vs-serphouse.md)\n- [Kagi Search API vs Tavily API + MCP](https://www.anchorterminal.com/compare/kagi-search-vs-tavily-mcp.md)\n- [Linkup vs SERPHouse](https://www.anchorterminal.com/compare/linkup-vs-serphouse.md)\n- [Linkup vs Tavily API + MCP](https://www.anchorterminal.com/compare/linkup-vs-tavily-mcp.md)\n- [Mojeek Web Search API vs SERPHouse](https://www.anchorterminal.com/compare/mojeek-vs-serphouse.md)\n- [Mojeek Web Search API vs Tavily API + MCP](https://www.anchorterminal.com/compare/mojeek-vs-tavily-mcp.md)\n- [Parallel Search and Task APIs vs SERPHouse](https://www.anchorterminal.com/compare/parallel-search-api-vs-serphouse.md)\n- [Parallel Search and Task APIs vs Tavily API + MCP](https://www.anchorterminal.com/compare/parallel-search-api-vs-tavily-mcp.md)\n- [Perplexity Search API vs SERPHouse](https://www.anchorterminal.com/compare/perplexity-search-api-vs-serphouse.md)\n- [Perplexity Search API vs Tavily API + MCP](https://www.anchorterminal.com/compare/perplexity-search-api-vs-tavily-mcp.md)\n- [SearchAPI.io vs SERPHouse](https://www.anchorterminal.com/compare/searchapi-io-vs-serphouse.md)\n- [SearchAPI.io vs Tavily API + MCP](https://www.anchorterminal.com/compare/searchapi-io-vs-tavily-mcp.md)\n- [SerpApi vs SERPHouse](https://www.anchorterminal.com/compare/serpapi-vs-serphouse.md)\n- [SerpApi vs Tavily API + MCP](https://www.anchorterminal.com/compare/serpapi-vs-tavily-mcp.md)\n- [Serper vs SERPHouse](https://www.anchorterminal.com/compare/serper-vs-serphouse.md)\n- [Serper vs Tavily API + MCP](https://www.anchorterminal.com/compare/serper-vs-tavily-mcp.md)\n- [SERPHouse vs SpecStream](https://www.anchorterminal.com/compare/serphouse-vs-specstream.md)\n- [SERPHouse vs TinyFish Search](https://www.anchorterminal.com/compare/serphouse-vs-tinyfish-search.md)\n- [SERPHouse vs Valyu](https://www.anchorterminal.com/compare/serphouse-vs-valyu.md)\n- [SERPHouse vs You.com APIs](https://www.anchorterminal.com/compare/serphouse-vs-you-com-api.md)\n- [SerpKite vs Tavily API + MCP](https://www.anchorterminal.com/compare/serpkite-vs-tavily-mcp.md)\n- [Tavily API + MCP vs TinyFish Search](https://www.anchorterminal.com/compare/tavily-mcp-vs-tinyfish-search.md)\n- [Tavily API + MCP vs Valyu](https://www.anchorterminal.com/compare/tavily-mcp-vs-valyu.md)\n- [Tavily API + MCP vs You.com APIs](https://www.anchorterminal.com/compare/tavily-mcp-vs-you-com-api.md)\n- [Arcmira vs Tavily API + MCP](https://www.anchorterminal.com/compare/arcmira-vs-tavily-mcp.md)\n- [Grep AI vs Tavily API + MCP](https://www.anchorterminal.com/compare/grep-ai-vs-tavily-mcp.md)\n- [Liner Search MCP vs Tavily API + MCP](https://www.anchorterminal.com/compare/liner-mcp-vs-tavily-mcp.md)\n- [SpecStream vs Tavily API + MCP](https://www.anchorterminal.com/compare/specstream-vs-tavily-mcp.md)\n- [Fetch (MCP reference server) vs SERPHouse](https://www.anchorterminal.com/compare/fetch-reference-server-vs-serphouse.md)\n- [Fetch (MCP reference server) vs Tavily API + MCP](https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp.md)\n- [NewsCatcher vs SERPHouse](https://www.anchorterminal.com/compare/newscatcher-vs-serphouse.md)\n- [NewsCatcher vs Tavily API + MCP](https://www.anchorterminal.com/compare/newscatcher-vs-tavily-mcp.md)\n- [Liner Search MCP vs SERPHouse](https://www.anchorterminal.com/compare/liner-mcp-vs-serphouse.md)\n- [SERPHouse vs SerpKite](https://www.anchorterminal.com/compare/serphouse-vs-serpkite.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "SERPHouse vs Tavily API + MCP", "url": "" } ], "description": "Tavily scores 77.1 (BB) to SERPHouse's 42.4 (E) for web search. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "SERPHouse E 42.4", "Tavily API + MCP BB 77.1", "scores" ], "h1": "SERPHouse vs Tavily API + MCP", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/serphouse-vs-tavily-mcp", "published": "2026-10-01", "section": "tools", "title": "SERPHouse vs Tavily for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/serphouse-vs-tavily-mcp" }, "tokens": { "markdown": 6050, "slim": 3530 }, "version": 1 }