{ "data": { "a": { "slug": "arcmira", "name": "Arcmira", "vendor": "Arcmira, Inc.", "vendorUrl": "https://arcmira.com", "kind": "mcp", "category": "search", "summary": "Arcmira indexes YouTube and podcast transcripts and returns timestamped passages, entity mentions, channel sponsors and mention alerts through a remote MCP server, a REST API at api.arcmira.com/v1, a CLI and TypeScript and Python SDKs.", "url": "https://www.anchorterminal.com/tools/arcmira", "markdownUrl": "https://www.anchorterminal.com/tools/arcmira.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/arcmira.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/arcmira.json", "repo": "https://github.com/arcmira/mcp", "license": "Proprietary service under Arcmira's Terms of Service. The MCP server's source is public under an all-rights-reserved notice; the Claude Code plugin, the arcmira TypeScript SDK and CLI and the Python SDK are Apache-2.0, and the Famous rankings are CC BY 4.0", "transports": [ "streamable-http", "http" ], "remoteUrl": "https://mcp.arcmira.com/mcp", "packages": [ { "registry": "npm", "name": "arcmira" }, { "registry": "pypi", "name": "arcmira" } ], "auth": "mixed", "authNotes": "The MCP server at https://mcp.arcmira.com/mcp answers an unauthenticated request with 401 and OAuth protected-resource metadata; hosts sign in through api.arcmira.com with the authorization code flow, PKCE S256, dynamic client registration and refresh tokens, and the consent screen grants read access plus, if allowed, monitor changes (scopes read, monitors:write, trackers:write, recommendations:read). Any client can instead send an account key as `Authorization: Bearer arc_sk_...`. Dashboard keys carry all four scopes and show once; a key minted from `POST /v1/signups` and `/v1/signups/verify` (an email and a six-digit code, no browser) carries `read` only and never expires. Keys are disabled on the API keys page and take effect at once; hosts are revoked under Dashboard, Integrations. Plan gates, not scopes, decide Premium transcripts, fresh media and sponsor rows.", "pricing": "freemium", "pricingNotes": "Free plan with 1,000 credits a month, 2 monitored names and no card, which withholds the newest 30 days of media and the pages past the first. Pro $20 a month for 20,000 credits (7-day trial, card required), Pro+ $60 for 60,000 with sponsor and recommendation rows, Ultra $200 for 400,000, Enterprise by contract; yearly billing 20 per cent less. A search passage, mention or list row costs 4 credits past the first 5 of a request, a momentum call 10, a sponsor row 40, a monitor alert 25, captions 4 per started 15 minutes and a Premium transcript 300 per started 15 minutes of the whole video, once. Past the plan, on-demand usage costs $0.002 a credit up to a budget an admin sets; repeating a request within 7 days and failed Premium transcripts cost nothing (https://arcmira.com/docs/usage-and-billing.md, checked 2026-10-30).", "priceSummary": "$0.001 / credit", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the OpenAPI file, llms.txt, developers.md, the docs or the pricing page (checked 2026-10-30). Paid plans and on-demand usage are billed to a card through Stripe from the dashboard.", "endpoints": [] }, "toolCount": 4, "popularity": { "githubStars": 78, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-30" }, "docsUrl": "https://arcmira.com/docs", "llmsTxt": "https://arcmira.com/llms.txt", "openapi": "https://api.arcmira.com/v1/openapi.json", "registryName": "io.github.arcmira/arcmira", "capabilities": [ "search.research", "audio.transcribe", "social.analytics" ], "tags": [ "hosted", "official", "closed-source", "openapi", "llms-txt", "mcp", "oauth", "cli", "typescript", "python", "webhooks", "free-tier", "no-card", "freemium", "pre-1.0", "agent-skills", "new" ], "lastRelease": "2026-10-15", "graded": true, "anchor": { "graded": true, "score": 64.2, "grade": "B", "agentReady": false, "rank": 420, "ranked": true, "rankOf": 1227, "categoryRank": 11, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 91, "maintenance": 84, "payments": 55, "reliability": 40, "schema": 87, "security": 61, "transparency": 61 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-30" }, "negative": -3, "negativeNotes": [ "Between 5 and 8 October 2026 the v1 API retired POST /v1/trackers (410 tracker_create_retired) and six tracker delivery fields for the team account model. The changelog says the first seven rows can break a client, and its entry is dated 8 October, the day the change finished, with no advance notice found. Documented the same day with typed codes, a 410 and a migration table, so deducted at the low end (-3). https://arcmira.com/docs/changelog.md" ], "verdict": "Four code-mode tools over a documented v1 API, OAuth 2.1 with four scopes, a read-only sign-up key from two API calls and no card, and a 1,000-credit free month. No status page, SLA or security.txt, breaking v1 changes shipped in October with same-day notice, the server is at 0.10.7, and the index covers the shows Arcmira transcribes.", "bestFor": "Agents answering what was said on YouTube shows and podcasts, who was mentioned or appeared where, which brands sponsor a show and how a name's mentions are trending, with timestamped source links, through one connection on a free monthly allowance.", "strengths": [ "OAuth 2.1 for MCP hosts with PKCE S256, dynamic client registration, refresh tokens, revocation and four scopes, plus bearer keys that are read-only when minted from the API", "A public OpenAPI 3.1 file of 35 operations, an error catalogue of about 60 codes with `unlock.url` and `details.limit`, `Idempotency-Key` on every write and a request id on every response", "Four tools whose programs run in an isolate that never holds the key, bounded to 40 API calls, 30 seconds and 12,000 characters, with all four annotations declared", "Free plan of 1,000 credits a month without a card, prices in credits per read published on one page, and a key from two API calls with an email and a code", "Published limits of 60, 240 and 600 requests a minute by plan, `RateLimit-*` headers on every response and `Retry-After` on 429, and HMAC-SHA256 signed webhooks with secret rotation" ], "weaknesses": [ "No status page, incident history or SLA was found; the terms disclaim uninterrupted service and Enterprise lists priority support without an uptime commitment", "No security.txt on any of the three hosts, no disclosure policy, bug bounty or certification, and the terms forbid probing for vulnerabilities", "The v1 API retired `POST /v1/trackers` and six tracker fields between 5 and 8 October 2026 with the changelog entry dated the day the change finished; the quickstart says routes arrive without notice", "The MCP server is at 0.10.7 after 30 releases in six weeks and two rounds of tool renames; the Free plan withholds the newest 30 days of media and pages past the first", "Every tool call, including the first 4,000 characters of the program and the agent's intent, is logged to the vendor's analytics with no opt-out, and the privacy policy states no retention periods", "Results are third-party speech with no prompt-injection guidance beyond checking the linked source, and support is one email address with no community channel" ], "agentNotes": [ "Call `arcmira_describe` once per session and write one program per question for `arcmira_execute_read`; return only the fields the answer needs, since output is cut at 12,000 characters and 3,000 per string.", "Resolve names with `arcmira.resolve` (free) before any `about`, `by`, `entity_ids` or `channel` filter; a name in a filter fails with `id_required`. Plain keyword search needs no resolver call.", "Check `arcmira.status()` or GET /v1/me for the plan, scopes and `usage.credits.available` before metered reads; on Free, media newer than 30 days and pages past the first fail with `freshness_requires_paid` and `pagination_gated`.", "A Premium read of an untranscribed video starts a transcription that uses credits (300 per started 15 minutes) and may return `pending`; read the same video again later, which is never charged twice, and send `retry: true` only when the user asks.", "Over HTTP send `Authorization: Bearer arc_sk_...`, an `Idempotency-Key` on every POST and PATCH, honour `Retry-After` on 429, and switch on `error.code`, following `unlock.url` on 402 and 403 rather than re-authenticating.", "Use `arcmira_execute_write` only after listing the user's monitors; it creates, follows and pauses but never deletes, and a connection made before server 0.9.0 answers `insufficient_scope` until reconnected." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.2 } ], "editorialScores": { "ergonomics": 91, "maintenance": 84, "payments": 55, "reliability": 40, "schema": 87, "security": 61, "transparency": 48 }, "provenanceScore": 73, "checked": { "categories": { "ergonomics": "2026-10-30", "maintenance": "2026-10-30", "payments": "2026-10-30", "reliability": "2026-10-30", "schema": "2026-10-30", "security": "2026-10-30", "transparency": "2026-10-30" }, "last": "2026-10-30", "lastMoved": "2026-10-30", "oldest": "2026-10-30", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install arcmira", "http": "curl 'https://api.arcmira.com/v1/search?q=corporate%20cards\u0026limit=5' -H \"Authorization: Bearer $ARCMIRA_API_KEY\"", "claudeCode": "claude mcp add --transport http --scope user arcmira https://mcp.arcmira.com/mcp", "config": { "mcpServers": { "arcmira": { "url": "https://mcp.arcmira.com/mcp" } } } }, "letme": { "capability": "https://letme.dev/search.research", "tool": "https://letme.dev/arcmira" }, "area": "web-data", "unitPrices": [ { "item": "Search passage, mention or list row (Pro plan credit)", "unit": "credit", "usd": 0.001, "note": "a plan credit on Pro and Pro+; a passage, mention or list row costs 4 credits past the first 5 of a request, so a request of 5 or fewer rows costs nothing; $0.0005 a credit on Ultra" }, { "item": "On-demand credit", "unit": "credit", "usd": 0.002, "note": "usage past the plan's credits, up to an admin-set monthly budget, invoiced in steps from $20" }, { "item": "Premium transcript, 15 minutes", "unit": "call", "usd": 0.3, "note": "300 credits per started 15 minutes of the whole video, once per account, at $0.001 a Pro plan credit; $0.60 on-demand, $0.15 on Ultra" }, { "item": "Monitor alert", "unit": "call", "usd": 0.025, "note": "25 credits at $0.001 a Pro plan credit; $0.05 on-demand" }, { "item": "Sponsor or commercial row", "unit": "record", "usd": 0.04, "note": "40 credits, Pro+ and above only, at $0.001 a plan credit" }, { "item": "Pro plan", "unit": "month", "usd": 20, "note": "20,000 credits a month, 10 monitored names, 7-day trial with a card; Pro+ $60 for 60,000, Ultra $200 for 400,000; yearly billing 20 per cent less" } ], "provenance": { "legalEntity": "Arcmira, Inc.", "domain": "arcmira.com", "domainRegistered": "2014-06-05", "endpointOnVendorDomain": true, "terms": "https://arcmira.com/terms", "privacy": "https://arcmira.com/privacy", "statusPage": "", "changelog": "https://arcmira.com/docs/changelog", "securityTxt": "none", "checked": "2026-10-30", "notes": [ "The Terms of Service (effective 13 October 2026) and the privacy policy (effective 2 October 2026) name Arcmira, Inc., a company based in San Francisco, California, governed by California law with AAA consumer arbitration in San Francisco County. The contact address on both is contact@arcmira.com; support is hi@arcmira.com and sales is sales@arcmira.com.", "RDAP for arcmira.com gives a registration date of 2014-06-05 and a last change on 2024-09-10, the month the GitHub organisation was created (23 September 2024). The Wayback Machine holds captures of the domain from 2011 under earlier owners, so the registration date says nothing about the product's age.", "firstReleased is 2026-08-22, when the arcmira npm package was first published and the arcmira/arcmira repository's history begins. The vendor's docs changelog dates the first public API (v1.0.0) to April 2026 without a day, so the product is older than this date shows. The MCP server's first registry version, 0.3.0, is dated 4 September 2026.", "https://arcmira.com/.well-known/security.txt, https://api.arcmira.com/.well-known/security.txt and https://mcp.arcmira.com/.well-known/security.txt answer 404. https://arcmira.com/status, /about, /blog and /changelog answer 403 with 'Your request was blocked'; the static sitemap lists none of them.", "robots.txt on the three arcmira.com hosts disallows ClaudeBot, Claude-Web and anthropic-ai and allows Claude-User and Claude-SearchBot by name; the 30 October 2026 batch file records the decision to research on that basis. Paths disallowed for every agent (/api/, /dashboard, /search, /chat, /monitors and others) were not fetched." ], "score": 73 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/arcmira.json", "live": { "slug": "arcmira", "probe": { "target": "https://mcp.arcmira.com/mcp", "method": "mcp-initialize", "lastAt": "2026-10-30T17:21:26.033779545Z", "lastOk": true, "lastStatus": 401, "lastMs": 128, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 281, "p95ms24h": 465, "samples24h": 18, "samples30d": 18, "days": [ { "date": "2026-10-30", "probes": 18, "ok": 18 } ] }, "updatedAt": "2026-10-30T17:21:26.033779545Z" } }, "answer": "Tavily API + MCP scores 77 (BB) on agent readiness against Arcmira's 64.2 (B), and leads in 5 of 7 scored categories. Arcmira leads on agent ergonomics and security \u0026 auth.", "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", "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, "grade": "BB", "agentReady": true, "rank": 36, "ranked": true, "rankOf": 1227, "categoryRank": 1, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 81, "maintenance": 85, "payments": 75, "reliability": 90, "schema": 89, "security": 52, "transparency": 62 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-17" }, "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.", "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)", "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", "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 } ], "editorialScores": { "ergonomics": 81, "maintenance": 85, "payments": 75, "reliability": 90, "schema": 89, "security": 52, "transparency": 47 }, "provenanceScore": 77, "checked": { "categories": { "ergonomics": "2026-10-17", "maintenance": "2026-10-17", "payments": "2026-10-17", "reliability": "2026-10-17", "schema": "2026-10-17", "security": "2026-10-17", "transparency": "2026-10-17" }, "last": "2026-10-17", "lastMoved": "2026-10-27", "oldest": "2026-10-17", "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": "2026-10-17", "score": 77 }, "requirements": { "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": "2026-10-30T17:21:58.61550577Z", "lastOk": true, "lastStatus": 200, "lastMs": 253, "lastNote": "initialize answered", "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 264, "p95ms24h": 357, "samples24h": 250, "samples30d": 8168, "days": [ { "date": "2026-09-29", "probes": 286, "ok": 286 }, { "date": "2026-09-30", "probes": 286, "ok": 286 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "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": 181, "ok": 181 } ] }, "vendorStatus": { "page": "https://status.tavily.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-30T17:21:58.443172524Z" }, "versions": [ { "registry": "mcp-registry", "name": "io.github.tavily-ai/tavily-mcp", "version": "0.2.15", "seenAt": "2026-10-30T14:54:40.546478788Z" }, { "registry": "npm", "name": "@tavily/core", "version": "0.7.14", "seenAt": "2026-10-30T14:49:07.228405539Z" }, { "registry": "npm", "name": "tavily-mcp", "version": "0.2.22", "seenAt": "2026-10-30T14:49:08.270739698Z" }, { "registry": "pypi", "name": "tavily-python", "version": "0.8.5", "released": "2026-10-06", "seenAt": "2026-10-30T14:49:08.081787358Z" } ], "githubStars": 2464, "npmWeekly": 467714, "pypiWeekly": 1636707, "securityTxt": { "url": "https://tavily.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-30T15:38:09.067896173Z" }, "llmsTxt": { "url": "https://docs.tavily.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-30T15:08:53.497451333Z" }, "domain": { "domain": "tavily.com", "registered": "2023-04-13", "source": "https://rdap.verisign.com/com/v1/domain/tavily.com", "checkedAt": "2026-10-25T13:54:33.179877097Z" }, "pages": [ { "url": "https://docs.tavily.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-30T05:38:55.141668171Z", "changedAt": "2026-10-29T05:06:02.910526045Z", "fingerprint": "09b5891d2f71" }, { "url": "https://www.tavily.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-30T06:01:19.352647695Z", "changedAt": "2026-10-30T06:01:19.352647695Z", "fingerprint": "faa220363671" }, { "url": "https://www.tavily.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-30T06:01:21.508978221Z", "changedAt": "2026-10-30T06:01:21.508978221Z", "fingerprint": "93c5b2b1e233" }, { "url": "https://www.tavily.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-30T06:01:24.057384431Z", "changedAt": "2026-10-30T06:01:24.057384431Z", "fingerprint": "48b828360e08" } ], "mcpTools": { "url": "https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e", "checkedAt": "2026-10-30T00:49:17.134017932Z", "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": "2026-10-26T08:09:33.10830208Z", "stars": 2460, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-22T05:48:57Z", "openIssues": 40, "openPRs": 23, "issuesOpened90d": 13, "issuesClosed90d": 3, "prsMerged90d": 11, "replies": { "sampled": 25, "unanswered": 21, "medianDays": 4.4 } }, "updatedAt": "2026-10-30T17:21:58.61550577Z" } }, "facts": [ { "a": "MCP server", "b": "MCP server", "name": "Kind" }, { "a": "Arcmira, Inc.", "b": "Tavily", "name": "Vendor" }, { "a": "https://mcp.arcmira.com/mcp", "b": "https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e", "name": "Hosted endpoint" }, { "a": "Streamable HTTP, HTTP", "b": "stdio, Streamable HTTP, HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth or key", "name": "Auth" }, { "a": "Freemium", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "payer tooling only", "name": "x402" }, { "a": "Proprietary service under Arcmira's Terms of Service. The MCP server's source is public under an all-rights-reserved notice; the Claude Code plugin, the arcmira TypeScript SDK and CLI and the Python SDK are Apache-2.0, and the Famous rankings are CC BY 4.0", "b": "MIT", "name": "Licence" }, { "a": "4", "b": "5", "name": "Tools exposed" }, { "a": "yes", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "io.github.arcmira/arcmira", "b": "io.github.tavily-ai/tavily-mcp", "name": "MCP registry" }, { "a": "2026-10-15", "b": "2026-10-06", "name": "Last release" }, { "a": "2026-10-13", "b": "2026-05-04", "name": "Terms last updated" }, { "a": "2026-10-02", "b": "2025-11-24", "name": "Privacy policy last updated" }, { "a": "yes", "b": "yes", "name": "Customer content may train models" }, { "a": "yes", "b": "yes", "name": "Terms restrict automated access" }, { "a": "yes", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "78 stars", "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 (BB) on agent readiness against Arcmira's 64.2 (B), and leads in 5 of 7 scored categories. Arcmira leads on agent ergonomics and security \u0026 auth.", "question": "Which is better for AI agents, Arcmira or Tavily API + MCP?" }, { "answer": "Both take an API key or an OAuth sign-in.", "question": "Do Arcmira and Tavily API + MCP need an API key?" }, { "answer": "Yes. Arcmira has a hosted endpoint at https://mcp.arcmira.com/mcp and Tavily API + MCP at https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e.", "question": "Can an agent call Arcmira and Tavily API + MCP without installing anything?" }, { "answer": "No open-source release is listed for Arcmira. Tavily API + MCP is open source (MIT).", "question": "Are Arcmira and Tavily API + MCP open source?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 91 against 81", "Security \u0026 auth, 61 against 52" ], "also": null, "goodFor": "Agents answering what was said on YouTube shows and podcasts, who was mentioned or appeared where, which brands sponsor a show and how a name's mentions are trending, with timestamped source links, through one connection on a free monthly allowance.", "slug": "arcmira", "watchFor": "No status page, incident history or SLA was found; the terms disclaim uninterrupted service and Enterprise lists priority support without an uptime commitment" }, { "aheadOn": [ "Reliability, 90 against 40", "Payments \u0026 pricing, 75 against 55" ], "also": [ "Agent-ready, a grade of BB or better", "Runs on your own machine", "Open source", "No incidents deducted, where Arcmira loses 3 points for them" ], "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" } ], "job": { "capability": "search.research", "name": "Research search" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-arcmira.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Arcmira", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-arcmira" }, { "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/arcmira-vs-brave-search-mcp.json", "title": "Arcmira vs Brave Search API + MCP", "url": "https://www.anchorterminal.com/compare/arcmira-vs-brave-search-mcp" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-cloudflare-web-search.json", "title": "Arcmira vs Cloudflare Web Search API", "url": "https://www.anchorterminal.com/compare/arcmira-vs-cloudflare-web-search" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-deepseek-search-api.json", "title": "Arcmira vs DeepSeek Search and Fetch API", "url": "https://www.anchorterminal.com/compare/arcmira-vs-deepseek-search-api" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-firecrawl-mcp.json", "title": "Arcmira vs Firecrawl MCP", "url": "https://www.anchorterminal.com/compare/arcmira-vs-firecrawl-mcp" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-kagi-search.json", "title": "Arcmira vs Kagi Search API", "url": "https://www.anchorterminal.com/compare/arcmira-vs-kagi-search" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-searchapi-io.json", "title": "Arcmira vs SearchAPI.io", "url": "https://www.anchorterminal.com/compare/arcmira-vs-searchapi-io" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-serpapi.json", "title": "Arcmira vs SerpApi", "url": "https://www.anchorterminal.com/compare/arcmira-vs-serpapi" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-serper.json", "title": "Arcmira vs Serper", "url": "https://www.anchorterminal.com/compare/arcmira-vs-serper" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-serpkite.json", "title": "Arcmira vs SerpKite", "url": "https://www.anchorterminal.com/compare/arcmira-vs-serpkite" }, { "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-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-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-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-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-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/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/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-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-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/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-exa-mcp.json", "title": "Arcmira vs Exa API + MCP", "url": "https://www.anchorterminal.com/compare/arcmira-vs-exa-mcp" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-grep-ai.json", "title": "Arcmira vs Grep AI", "url": "https://www.anchorterminal.com/compare/arcmira-vs-grep-ai" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-linkup.json", "title": "Arcmira vs Linkup", "url": "https://www.anchorterminal.com/compare/arcmira-vs-linkup" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-parallel-search-api.json", "title": "Arcmira vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/arcmira-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-tinyfish-search.json", "title": "Arcmira vs TinyFish Search", "url": "https://www.anchorterminal.com/compare/arcmira-vs-tinyfish-search" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-valyu.json", "title": "Arcmira vs Valyu", "url": "https://www.anchorterminal.com/compare/arcmira-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-you-com-api.json", "title": "Arcmira vs You.com APIs", "url": "https://www.anchorterminal.com/compare/arcmira-vs-you-com-api" }, { "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/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" } ], "scores": [ { "arcmira": 40, "by": 50, "edge": "tavily-mcp", "key": "reliability", "name": "Reliability", "tavily-mcp": 90, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "arcmira": 87, "by": 2, "edge": "tavily-mcp", "key": "schema", "name": "Schema \u0026 documentation", "tavily-mcp": 89, "weight": 13 }, { "arcmira": 91, "by": 10, "edge": "arcmira", "key": "ergonomics", "name": "Agent ergonomics", "tavily-mcp": 81, "weight": 13 }, { "arcmira": 61, "by": 9, "edge": "arcmira", "key": "security", "name": "Security \u0026 auth", "tavily-mcp": 52, "weight": 14 }, { "arcmira": 55, "by": 20, "edge": "tavily-mcp", "key": "payments", "name": "Payments \u0026 pricing", "tavily-mcp": 75, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "arcmira": 84, "by": 1, "edge": "tavily-mcp", "key": "maintenance", "name": "Maintenance \u0026 community", "tavily-mcp": 85, "weight": 7 }, { "arcmira": 61, "by": 1, "edge": "tavily-mcp", "key": "transparency", "name": "Transparency \u0026 trust", "tavily-mcp": 62, "weight": 7 } ], "summary": "Tavily API + MCP scores 77 (BB) on agent readiness against Arcmira's 64.2 (B), and leads in 5 of 7 scored categories. Arcmira leads on agent ergonomics and security \u0026 auth. Both do research search.", "tutorials": [], "verdicts": { "arcmira": "Four code-mode tools over a documented v1 API, OAuth 2.1 with four scopes, a read-only sign-up key from two API calls and no card, and a 1,000-credit free month. No status page, SLA or security.txt, breaking v1 changes shipped in October with same-day notice, the server is at 0.10.7, and the index covers the shows Arcmira transcribes.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/arcmira-vs-tavily-mcp", "json": "https://www.anchorterminal.com/compare/arcmira-vs-tavily-mcp.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/arcmira-vs-tavily-mcp.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/arcmira-vs-tavily-mcp.min.md" }, "markdown": "Tavily API + MCP scores 77 (BB) on agent readiness against Arcmira's 64.2 (B), and leads in 5 of 7 scored categories. Arcmira leads on agent ergonomics and security \u0026 auth. Both do research search.\n\n- Arcmira: grade B, 64.2/100, rank #420 of 1227. Markdown https://www.anchorterminal.com/tools/arcmira.md · JSON https://www.anchorterminal.com/api/v1/tools/arcmira.json\n- Tavily API + MCP: grade BB, 77/100, rank #36 of 1227. 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 182 search comparisons: https://www.anchorterminal.com/compare/search/index.md\n\n## Which one, for what\n\n### Arcmira (B)\n\nGood for: Agents answering what was said on YouTube shows and podcasts, who was mentioned or appeared where, which brands sponsor a show and how a name's mentions are trending, with timestamped source links, through one connection on a free monthly allowance.\n\nAhead on:\n- Agent ergonomics, 91 against 81\n- Security \u0026 auth, 61 against 52\n\nWatch for: No status page, incident history or SLA was found; the terms disclaim uninterrupted service and Enterprise lists priority support without an uptime commitment\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- Payments \u0026 pricing, 75 against 55\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Runs on your own machine\n- Open source\n- No incidents deducted, where Arcmira loses 3 points for them\n\nWatch for: x402 covers advanced search only, not extract, map, crawl or research\n\n\n## Score by category\n\n| Category | Weight | Arcmira | 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) | 87 | 89 | Tavily API + MCP +2 |\n| Agent ergonomics | 13% (16.2 this run) | 91 | 81 | Arcmira +10 |\n| Security \u0026 auth | 14% (17.5 this run) | 61 | 52 | Arcmira +9 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 55 | 75 | Tavily API + MCP +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 84 | 85 | Tavily API + MCP +1 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 61 | 62 | Tavily API + MCP +1 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **64.2 · B** | **77 · BB** | |\n\n## Facts side by side\n\n| Fact | Arcmira | Tavily API + MCP |\n| --- | --- | --- |\n| Kind | MCP server | MCP server |\n| Vendor | Arcmira, Inc. | Tavily |\n| Hosted endpoint | `https://mcp.arcmira.com/mcp` | `https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e` |\n| Transports | Streamable HTTP, HTTP | stdio, Streamable HTTP, HTTP |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Freemium | Freemium |\n| x402 | no | payer tooling only |\n| Licence | Proprietary service under Arcmira's Terms of Service. The MCP server's source is public under an all-rights-reserved notice; the Claude Code plugin, the arcmira TypeScript SDK and CLI and the Python SDK are Apache-2.0, and the Famous rankings are CC BY 4.0 | MIT |\n| Tools exposed | 4 | 5 |\n| Read-only variant documented | yes | no |\n| llms.txt | yes | yes |\n| MCP registry | `io.github.arcmira/arcmira` | `io.github.tavily-ai/tavily-mcp` |\n| Last release | 2026-10-15 | 2026-10-06 |\n| Terms last updated | 2026-10-13 | 2026-05-04 |\n| Privacy policy last updated | 2026-10-02 | 2025-11-24 |\n| Customer content may train models | yes | yes |\n| Terms restrict automated access | yes | yes |\n| Terms restrict benchmarking | yes | yes |\n| Terms or service can change without notice | yes | yes |\n| Arbitration or class-action waiver | yes | yes |\n| Popularity | 78 stars | 2.4k stars, 452k npm/wk, 1.6M PyPI/wk |\n| Agent reviews | none | 3.6/5 (8) |\n\n## Verdicts\n\n**Arcmira.** Four code-mode tools over a documented v1 API, OAuth 2.1 with four scopes, a read-only sign-up key from two API calls and no card, and a 1,000-credit free month. No status page, SLA or security.txt, breaking v1 changes shipped in October with same-day notice, the server is at 0.10.7, and the index covers the shows Arcmira transcribes.\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.\n\n## Before you call either\n\n### Arcmira\n\n1. Call `arcmira_describe` once per session and write one program per question for `arcmira_execute_read`; return only the fields the answer needs, since output is cut at 12,000 characters and 3,000 per string.\n2. Resolve names with `arcmira.resolve` (free) before any `about`, `by`, `entity_ids` or `channel` filter; a name in a filter fails with `id_required`. Plain keyword search needs no resolver call.\n3. Check `arcmira.status()` or GET /v1/me for the plan, scopes and `usage.credits.available` before metered reads; on Free, media newer than 30 days and pages past the first fail with `freshness_requires_paid` and `pagination_gated`.\n4. A Premium read of an untranscribed video starts a transcription that uses credits (300 per started 15 minutes) and may return `pending`; read the same video again later, which is never charged twice, and send `retry: true` only when the user asks.\n5. Over HTTP send `Authorization: Bearer arc_sk_...`, an `Idempotency-Key` on every POST and PATCH, honour `Retry-After` on 429, and switch on `error.code`, following `unlock.url` on 402 and 403 rather than re-authenticating.\n6. Use `arcmira_execute_write` only after listing the user's monitors; it creates, follows and pauses but never deletes, and a connection made before server 0.9.0 answers `insufficient_scope` until reconnected.\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\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, Arcmira or Tavily API + MCP?\n\nTavily API + MCP scores 77 (BB) on agent readiness against Arcmira's 64.2 (B), and leads in 5 of 7 scored categories. Arcmira leads on agent ergonomics and security \u0026 auth.\n\n### Do Arcmira and Tavily API + MCP need an API key?\n\nBoth take an API key or an OAuth sign-in.\n\n### Can an agent call Arcmira and Tavily API + MCP without installing anything?\n\nYes. Arcmira has a hosted endpoint at https://mcp.arcmira.com/mcp and Tavily API + MCP at https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e.\n\n### Are Arcmira and Tavily API + MCP open source?\n\nNo open-source release is listed for Arcmira. Tavily API + MCP is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/arcmira-vs-tavily-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/arcmira-vs-tavily-mcp.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"arcmira\", \"b\": \"tavily-mcp\"}`. From a terminal: `anchor compare arcmira tavily-mcp`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/arcmira.json and https://www.anchorterminal.com/api/v1/tools/tavily-mcp.json\n\n## Other comparisons with Arcmira or Tavily API + MCP\n\n- [Web Search Tool on Amazon Bedrock AgentCore vs Arcmira](https://www.anchorterminal.com/compare/agentcore-web-search-vs-arcmira.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- [Arcmira vs Brave Search API + MCP](https://www.anchorterminal.com/compare/arcmira-vs-brave-search-mcp.md)\n- [Arcmira vs Cloudflare Web Search API](https://www.anchorterminal.com/compare/arcmira-vs-cloudflare-web-search.md)\n- [Arcmira vs DeepSeek Search and Fetch API](https://www.anchorterminal.com/compare/arcmira-vs-deepseek-search-api.md)\n- [Arcmira vs Firecrawl MCP](https://www.anchorterminal.com/compare/arcmira-vs-firecrawl-mcp.md)\n- [Arcmira vs Kagi Search API](https://www.anchorterminal.com/compare/arcmira-vs-kagi-search.md)\n- [Arcmira vs SearchAPI.io](https://www.anchorterminal.com/compare/arcmira-vs-searchapi-io.md)\n- [Arcmira vs SerpApi](https://www.anchorterminal.com/compare/arcmira-vs-serpapi.md)\n- [Arcmira vs Serper](https://www.anchorterminal.com/compare/arcmira-vs-serper.md)\n- [Arcmira vs SerpKite](https://www.anchorterminal.com/compare/arcmira-vs-serpkite.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 Tavily API + MCP](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-tavily-mcp.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 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 Tavily API + MCP](https://www.anchorterminal.com/compare/kagi-search-vs-tavily-mcp.md)\n- [Linkup vs Tavily API + MCP](https://www.anchorterminal.com/compare/linkup-vs-tavily-mcp.md)\n- [Parallel Search and Task APIs vs Tavily API + MCP](https://www.anchorterminal.com/compare/parallel-search-api-vs-tavily-mcp.md)\n- [SearchAPI.io vs Tavily API + MCP](https://www.anchorterminal.com/compare/searchapi-io-vs-tavily-mcp.md)\n- [SerpApi vs Tavily API + MCP](https://www.anchorterminal.com/compare/serpapi-vs-tavily-mcp.md)\n- [Serper vs Tavily API + MCP](https://www.anchorterminal.com/compare/serper-vs-tavily-mcp.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 Exa API + MCP](https://www.anchorterminal.com/compare/arcmira-vs-exa-mcp.md)\n- [Arcmira vs Grep AI](https://www.anchorterminal.com/compare/arcmira-vs-grep-ai.md)\n- [Arcmira vs Linkup](https://www.anchorterminal.com/compare/arcmira-vs-linkup.md)\n- [Arcmira vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/arcmira-vs-parallel-search-api.md)\n- [Arcmira vs TinyFish Search](https://www.anchorterminal.com/compare/arcmira-vs-tinyfish-search.md)\n- [Arcmira vs Valyu](https://www.anchorterminal.com/compare/arcmira-vs-valyu.md)\n- [Arcmira vs You.com APIs](https://www.anchorterminal.com/compare/arcmira-vs-you-com-api.md)\n- [Grep AI vs Tavily API + MCP](https://www.anchorterminal.com/compare/grep-ai-vs-tavily-mcp.md)\n- [Fetch (MCP reference server) vs Tavily API + MCP](https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp.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": "2026-10-30", "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": "Arcmira vs Tavily API + MCP", "url": "" } ], "description": "Tavily scores 77 (BB) to Arcmira's 64.2 (B) for research search. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Arcmira B 64.2", "Tavily API + MCP BB 77", "scores" ], "h1": "Arcmira vs Tavily API + MCP", "image": "https://www.anchorterminal.com/assets/og/compare-arcmira-vs-tavily-mcp.png", "path": "/compare/arcmira-vs-tavily-mcp", "published": "2026-10-01", "section": "tools", "title": "Arcmira vs Tavily for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-30", "url": "https://www.anchorterminal.com/compare/arcmira-vs-tavily-mcp" }, "tokens": { "markdown": 3050, "slim": 730 }, "version": 1 }