{ "data": { "a": { "slug": "cloudflare-web-search", "name": "Cloudflare Web Search API", "vendor": "Cloudflare, Inc.", "vendorUrl": "https://www.cloudflare.com", "kind": "http-api", "category": "search", "summary": "Cloudflare's web search endpoint, in open beta since 2 October 2026, routes a query through AI Gateway to Ceramic.ai, Exa or Linkup and returns results in one format, by REST or from a Worker's AI binding.", "url": "https://www.anchorterminal.com/tools/cloudflare-web-search", "markdownUrl": "https://www.anchorterminal.com/tools/cloudflare-web-search.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cloudflare-web-search.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cloudflare-web-search.json", "license": "Proprietary service under Cloudflare's terms. Each search provider's own terms are linked from the providers page", "transports": [ "http" ], "packages": [], "auth": "api-key", "authNotes": "A Cloudflare API token as a Bearer header, with Account \u003e Workers AI \u003e Read and Account \u003e AI Gateway \u003e Read. Inside a Worker the `AI` binding needs no token. Provider keys stored on the gateway (BYOK) are selected by `byokAlias` and never sent in the request. The OpenAPI operation also accepts the legacy global API key with an email header.", "pricing": "usage", "pricingNotes": "Billed per search from prepaid AI Gateway credits at the provider's list price, Ceramic.ai $0.25, Linkup $5.00 and Exa $7.00 per 1,000 requests. Credits carry a 5 per cent purchase fee and need a payment method on the account. With a stored provider key the provider bills you directly. No free allowance found (https://developers.cloudflare.com/web-search/providers/, checked 2026-10-05).", "priceSummary": "$0.25 / 1k req", "where": "local", "x402": { "level": "no", "evidence": "AI Gateway Machine Payments (x402, beta since 30 September 2026) covers only POST /ai/run for four open models, US accounts with a card on file. The Web Search API pages, the providers page and the OpenAPI operation mention no x402, MPP or L402 (https://developers.cloudflare.com/ai-gateway/features/machine-payments/, checked 2026-10-05).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-05" }, "docsUrl": "https://developers.cloudflare.com/web-search/", "llmsTxt": "https://developers.cloudflare.com/web-search/llms.txt", "openapi": "https://raw.githubusercontent.com/cloudflare/api-schemas/main/openapi.json", "capabilities": [ "web.search" ], "tags": [ "hosted", "beta", "openapi", "llms-txt", "typescript", "status-page", "bug-bounty" ], "lastRelease": "2026-10-02", "graded": true, "anchor": { "graded": true, "score": 62.1, "grade": "B", "agentReady": false, "rank": 226, "ranked": true, "rankOf": 460, "categoryRank": 10, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 63, "maintenance": 71, "payments": 20, "reliability": 55, "schema": 81, "security": 71, "transparency": 75 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-05" }, "negative": 0, "verdict": "One endpoint that sends a search to Ceramic.ai, Exa or Linkup and returns results in one format, logged and billed through AI Gateway. Ceramic.ai costs $0.25 per 1,000 searches. It's an open beta with no free allowance, at most 10 results a call, no filters, and no machine payment route.", "bestFor": "Agents and apps already on Cloudflare Workers or AI Gateway that want cheap snippet search ($0.25 per 1,000 with Ceramic.ai) on the same bill and logs as their inference.", "strengths": [ "Three providers behind one request shape, switched by the `provider` parameter", "Ceramic.ai at $0.25 per 1,000 searches, at the provider's list price", "Every search lands in AI Gateway logs, with per-request headers to skip storing payloads", "Typed error body with category, code and a `retryable` flag", "Providers commit to verified-bot crawling and a source link on every result" ], "weaknesses": [ "Open beta, with no SLA found for AI Gateway", "Credits need a payment method and carry a 5 per cent purchase fee. No free allowance", "At most 10 results a call, with no pagination, domain or date filters", "No x402. Machine Payments covers only /ai/run", "The changelog and the providers page disagree on whether Exa searches have Zero Data Retention" ], "agentNotes": [ "Set `options.gateway.id`. Every account has a gateway named `default`", "Pass `provider` explicitly. It defaults to Ceramic.ai, whose descriptions can run to 8,000 characters a result", "Set `limit` to the results you'll read, between 1 and 10", "Set `byokAlias` when you mean to use a stored provider key, so a missing key fails with 400 instead of spending credits", "Send `cf-aig-collect-log-payload: false` if queries shouldn't be stored in gateway logs" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.1 } ], "editorialScores": { "ergonomics": 63, "maintenance": 71, "payments": 20, "reliability": 55, "schema": 81, "security": 71, "transparency": 50 }, "provenanceScore": 100 }, "connect": { "http": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/websearch/ \\\n --request POST \\\n --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n --header \"Content-Type: application/json\" \\\n --data '{\n \"query\": \"What are some fun things to do in Salt Lake City as fall approaches?\",\n \"provider\": \"ceramic\",\n \"limit\": 5,\n \"options\": {\n \"gateway\": { \"id\": \"default\" }\n }\n }'" }, "letme": { "capability": "https://letme.dev/web.search", "tool": "https://letme.dev/cloudflare-web-search" }, "sameCompany": [ "cloudflare-sandbox-sdk", "cloudflare-mcp", "cloudflare-r2", "cloudflare-clef" ], "area": "web-data", "unitPrices": [ { "item": "Search, Ceramic.ai", "unit": "1k-requests", "usd": 0.25 }, { "item": "Search, Linkup", "unit": "1k-requests", "usd": 5 }, { "item": "Search, Exa", "unit": "1k-requests", "usd": 7 } ], "provenance": { "legalEntity": "Cloudflare, Inc.", "domain": "cloudflare.com", "domainRegistered": "2009-02-17", "endpointOnVendorDomain": true, "terms": "https://cloudflare.com/terms/", "privacy": "https://cloudflare.com/privacypolicy/", "statusPage": "https://www.cloudflarestatus.com", "changelog": "https://developers.cloudflare.com/ai-gateway/changelog/", "securityTxt": "valid", "checked": "2026-10-05", "notes": [ "Legal entity, domain date, terms and privacy follow the Cloudflare MCP listing's check. We didn't re-read them for this listing.", "www.cloudflare.com/.well-known/security.txt, read on 5 October 2026, names HackerOne and a disclosure policy and carries no Expires field.", "The endpoint is on api.cloudflare.com. Searches are forwarded to Ceramic.ai, Exa or Linkup." ], "score": 100 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cloudflare-web-search.json", "live": { "slug": "cloudflare-web-search", "vendorStatus": { "page": "https://www.cloudflarestatus.com", "indicator": "major", "summary": "Partial System Outage", "checkedAt": "2026-10-06T01:47:08.690984366Z" }, "updatedAt": "2026-10-06T01:47:08.690984366Z" } }, "answer": "Firecrawl MCP scores 75.5 (BB) on agent readiness against Cloudflare Web Search API's 62.1 (B), and leads in 6 of 7 scored categories.", "b": { "slug": "firecrawl-mcp", "name": "Firecrawl MCP", "vendor": "Firecrawl (Mendable)", "vendorUrl": "https://www.firecrawl.dev", "kind": "mcp", "category": "web-scrapers", "summary": "Official Firecrawl server for scraping pages to markdown/JSON, mapping and crawling sites, web search, browser interaction, monitoring and an autonomous research agent.", "url": "https://www.anchorterminal.com/tools/firecrawl-mcp", "markdownUrl": "https://www.anchorterminal.com/tools/firecrawl-mcp.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/firecrawl-mcp.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/firecrawl-mcp.json", "repo": "https://github.com/firecrawl/firecrawl-mcp-server", "license": "MIT", "transports": [ "stdio", "streamable-http", "sse" ], "remoteUrl": "https://mcp.firecrawl.dev/v2/mcp", "packages": [ { "registry": "npm", "name": "firecrawl-mcp" } ], "auth": "mixed", "authNotes": "Hosted endpoints take OAuth (`https://mcp.firecrawl.dev/v2/mcp-oauth`) or `Authorization: Bearer \u003cFIRECRAWL_API_KEY\u003e` on `https://mcp.firecrawl.dev/v2/mcp`. The same URL with no credential is the keyless tier (scrape, search, parse, rate-limited per IP). The search-only endpoint `/v2/mcp-search` has its own OAuth identity. Locally, FIRECRAWL_API_KEY or FIRECRAWL_OAUTH_TOKEN, or FIRECRAWL_API_URL for self-hosted. The README says never to put a key in the server URL. Endpoint- and format-locked keys are Enterprise only.", "pricing": "freemium", "pricingNotes": "Free 1,000 credits a month, no card. Hobby $19 a month or $16 billed yearly (5,000 credits), Standard $99 or $83 (100,000), Growth $399 or $333 (500,000), Scale $749 or $599 (1 million). Scrape, crawl and map cost 1 credit a page, search 2 per 10 results, interact 2 per browser-minute, monitor 1 per page per check, and JSON, question or highlight formats add 4 a page. $5 top-ups on paid plans only. A scrape with no result isn't charged, but a page returning 403 or 404 costs 1 credit (https://www.firecrawl.dev/pricing).", "priceSummary": "$19 / mo", "where": "both", "x402": { "level": "no", "evidence": "No x402 support in README, docs or pricing (checked 2026-09-25).", "endpoints": [] }, "toolCount": 26, "popularity": { "githubStars": 7500, "npmWeekly": 28853, "pypiWeekly": null, "asOf": "2026-09-26" }, "docsUrl": "https://github.com/firecrawl/firecrawl-mcp-server#readme", "llmsTxt": "https://docs.firecrawl.dev/llms.txt", "openapi": "https://docs.firecrawl.dev/api-reference/v2-openapi.json", "registryName": "io.github.firecrawl/firecrawl-mcp-server", "capabilities": [ "web.search", "web.fetch", "web.crawl", "web.extract" ], "tags": [ "official", "hosted", "local", "open-source", "freemium", "llms-txt" ], "lastRelease": "2026-10-01", "graded": true, "anchor": { "graded": true, "score": 75.5, "grade": "BB", "agentReady": true, "rank": 32, "ranked": true, "rankOf": 460, "categoryRank": 2, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 92, "maintenance": 87, "payments": 50, "reliability": 70, "schema": 88, "security": 67, "transparency": 76 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-10-01" }, "negative": 0, "verdict": "Keyless hosted endpoint with scrape, search and parse, plus OAuth and a search-only endpoint. No x402 or other machine payment.", "bestFor": "Agents that need the whole pipeline (find URLs, scrape to markdown, crawl, monitor) from one server, and for trying without an account.", "strengths": [ "Keyless hosted endpoint with scrape, search and parse, plus OAuth and a search-only endpoint", "Four incidents since July 2026, the longest 56 minutes", "Rate limits published per plan and per endpoint", "Public v2 OpenAPI, llms.txt and readOnly or destructive hints on every tool", "firecrawl-mcp 3.27.2 on 1 October 2026, after more than 20 releases since July" ], "weaknesses": [ "No x402 or other machine payment", "No prompt-injection guidance for scraped pages outside retained Alexandria results", "403 and 404 responses cost a credit", "Open issues report 132 undescribed parameters and a schema mismatch", "Privacy policy last revised December 2024, with no retention period for scraped content" ], "agentNotes": [ "Use `firecrawl_map` to list URLs, then scrape the few you need instead of crawling a whole site", "On the keyless endpoint only scrape, search and parse work. A 429 carries a `signup_url` for the human", "Ask for markdown only. JSON, question and highlight formats add 4 credits a page", "Poll `firecrawl_check_crawl_status` rather than waiting on a long crawl inside one call", "Check the URL before scraping. Dead pages still cost a credit" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 8, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "BB", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 75.5 } ], "editorialScores": { "ergonomics": 92, "maintenance": 87, "payments": 50, "reliability": 70, "schema": 88, "security": 67, "transparency": 60 }, "provenanceScore": 92 }, "connect": { "claudeCode": "claude mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcp", "config": { "mcpServers": { "firecrawl": { "args": [ "-y", "firecrawl-mcp" ], "command": "npx", "env": { "FIRECRAWL_API_KEY": "${FIRECRAWL_API_KEY}" } } } } }, "letme": { "capability": "https://letme.dev/web.search", "tool": "https://letme.dev/firecrawl-mcp" }, "area": "web-data", "unitPrices": [ { "item": "Hobby plan", "unit": "month", "usd": 19, "note": "5,000 credits. $16 a month billed yearly" }, { "item": "Standard plan", "unit": "month", "usd": 99, "note": "100,000 credits. $83 a month billed yearly" }, { "item": "Extra credits on Hobby", "unit": "1k-pages", "usd": 5, "note": "one credit scrapes one page" } ], "provenance": { "legalEntity": "SideGuide Technologies, Inc. (d/b/a Firecrawl)", "domain": "firecrawl.dev", "domainRegistered": "2024-04-08", "endpointOnVendorDomain": true, "terms": "https://firecrawl.dev/terms-of-service", "privacy": "https://firecrawl.dev/privacy-policy", "statusPage": "https://status.firecrawl.dev", "changelog": "https://firecrawl.dev/changelog", "securityTxt": "valid", "checked": "2026-09-26", "score": 92 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/firecrawl-mcp.json", "live": { "slug": "firecrawl-mcp", "probe": { "target": "https://mcp.firecrawl.dev/v2/mcp", "method": "mcp-initialize", "lastAt": "2026-10-06T01:46:29.444011571Z", "lastOk": true, "lastStatus": 200, "lastMs": 255, "lastNote": "initialize answered", "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 252, "p95ms24h": 328, "samples24h": 273, "samples30d": 2349, "days": [ { "date": "2026-09-27", "probes": 132, "ok": 132 }, { "date": "2026-09-28", "probes": 285, "ok": 285 }, { "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": 21, "ok": 21 } ] }, "vendorStatus": { "page": "https://status.firecrawl.dev", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-06T01:25:58.41491856Z" }, "versions": [ { "registry": "github", "name": "firecrawl/firecrawl-mcp-server", "version": "v3.2.1", "released": "2025-09-26", "seenAt": "2026-10-05T16:52:34.383149653Z" }, { "registry": "mcp-registry", "name": "io.github.firecrawl/firecrawl-mcp-server", "version": "3.27.3", "seenAt": "2026-10-05T23:55:54.568086057Z" }, { "registry": "npm", "name": "firecrawl-mcp", "version": "3.27.3", "seenAt": "2026-10-05T16:52:33.945428107Z" } ], "githubStars": 7553, "npmWeekly": 191569, "securityTxt": { "url": "https://firecrawl.dev/.well-known/security.txt", "state": "valid", "expires": "2027-06-10T00:00:00.000Z", "checkedAt": "2026-10-05T15:16:15.112419784Z" }, "llmsTxt": { "url": "https://docs.firecrawl.dev/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-05T15:19:01.388728404Z" }, "domain": { "domain": "firecrawl.dev", "registered": "2024-04-08", "source": "https://pubapi.registry.google/rdap/domain/firecrawl.dev", "checkedAt": "2026-10-04T13:08:05.084729774Z" }, "pages": [ { "url": "https://firecrawl.dev/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-05T15:57:00.504763665Z", "changedAt": "2026-10-05T15:57:00.504763665Z", "fingerprint": "c643c0d541cc" }, { "url": "https://www.firecrawl.dev/pricing", "kind": "deprecations", "status": 200, "checkedAt": "2026-10-05T16:02:35.008540289Z", "changedAt": "2026-10-05T16:02:35.008540289Z", "fingerprint": "5f06048f6c1e" }, { "url": "https://firecrawl.dev/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-05T15:57:03.64292004Z", "changedAt": "2026-10-05T15:57:03.64292004Z", "fingerprint": "40f2932bdf9b" }, { "url": "https://firecrawl.dev/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-10-05T15:57:04.984239801Z", "changedAt": "2026-10-05T15:57:04.984239801Z", "fingerprint": "3e9599bccfe2" } ], "mcpTools": { "url": "https://mcp.firecrawl.dev/v2/mcp", "checkedAt": "2026-10-05T22:30:59.534531678Z", "status": "ok", "protocol": "2025-11-25", "tools": [ { "name": "firecrawl_scrape", "title": "Firecrawl scrape", "description": "\nScrape one URL and return its content: markdown by default, or HTML, links, screenshots, branding data, a targeted answer, or JSON matching a supplied schema. Use it when the request identifies a page and needs its content or defined fields. Use `firecrawl_search` when additional web sources are needed; on an authenticated session, `firecrawl_map` lists a site's URLs and `firecrawl_crawl` collects a set of pages.\n\nFirecrawl may serve recently indexed content; set `maxAge: 0` for a live fetch or a smaller `maxAge` to bound staleness. A successful response does not by itself confirm the page is still current. Browser actions can change the live page when interactive actions are enabled. Authenticated responses can include a `metadata.scrapeId` for optional scrape feedback.\n\nOn an authenticated session with Alexandria access, `firecrawl_search` with `sources` unset and `firecrawl_find_tools` can discover providers for the same fields across several pages; a matching provider returns typed records in one call. Keyless sessions have no provider matches.\n\nAlexandria mode, on an authenticated session with Alexandria access: `alexandria` selects catalogued capability execution and is mutually exclusive with `url`.\n", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false, "properties": { "alexandria": { "anyOf": [ { "properties": { "capability": { "description": "Capability address as returned by search or discover, e.g. \"series/observations\".", "minLength": 1, "type": "string" }, "options": { "additionalProperties": {}, "description": "Capability options as declared by its contract.", "propertyNames": { "type": "string" }, "type": "object" }, "provider": { "description": "Provider slug, e.g. \"fred\".", "minLength": 1, "type": "string" }, "version": { "description": "Optional published workflow version. Omit to use the latest version.", "maxLength": 128, "minLength": 1, "type": "string" } }, "required": [ "provider", "capability" ], "type": "object" }, { "items": { "properties": { "capability": { "description": "Capability address as returned by search or discover, e.g. \"series/observations\".", "minLength": 1, "type": "string" }, "options": { "additionalProperties": {}, "description": "Capability options as declared by its contract.", "propertyNames": { "type": "string" }, "type": "object" }, "provider": { "description": "Provider slug, e.g. \"fred\".", "minLength": 1, "type": "string" }, "version": { "description": "Optional published workflow version. Omit to use the latest version.", "maxLength": 128, "minLength": 1, "type": "string" } }, "required": [ "provider", "capability" ], "type": "object" }, "maxItems": 10, "minItems": 1, "type": "array" } ], "description": "Catalogued Alexandria capability invocation, mutually exclusive with url. One {provider, capability, options} object or an array of 1-10, with contracts available through firecrawl_search or firecrawl_find_tools. Each call may include version to pin a published workflow; omitting it uses latest. Only requestId and timeout are supported alongside alexandria. The selected contract marks required inputs and any requiresOneOf groups (at least one member per group); it may include example.request/example.response and response.key (which may differ from records). Where pagination is declared, its fields govern paging with the same filters; catalogue next is separate from provider pagination. Returns per-capability results in data.alexandria with data, records, or an error with a code; individual capabilities can fail even when the outer response succeeds. Requires an API key on a team with Alexandria enabled. Some providers require accepted terms; blocked requests return the applicable requirements." }, "domainTools": { "description": "URL mode only: include domain-matched Alexandria tools for the page in tools on the returned document. Ignored with alexandria.", "type": "boolean" }, "excludeTags": { "items": { "type": "string" }, "type": "array" }, "formats": { "items": { "enum": [ "markdown", "html", "rawHtml", "screenshot", "links", "summary", "changeTracking", "branding", "json", "query", "audio" ], "type": "string" }, "type": "array" }, "includeTags": { "items": { "type": "string" }, "type": "array" }, "jsonOptions": { "additionalProperties": false, "properties": { "prompt": { "type": "string" }, "schema": { "additionalProperties": false, "propertyNames": { "type": "string" }, "type": "object" } }, "type": "object" }, "location": { "additionalProperties": false, "properties": { "country": { "type": "string" }, "languages": { "items": { "type": "string" }, "type": "array" } }, "type": "object" }, "lockdown": { "type": "boolean" }, "maxAge": { "type": "number" }, "mobile": { "type": "boolean" }, "onlyMainContent": { "type": "boolean" }, "parsers": { "items": { "enum": [ "pdf" ], "type": "string" }, "type": "array" }, "pdfOptions": { "additionalProperties": false, "properties": { "maxPages": { "maximum": 10000, "minimum": 1, "type": "integer" } }, "type": "object" }, "profile": { "additionalProperties": false, "properties": { "name": { "type": "string" }, "saveChanges": { "type": "boolean" } }, "required": [ "name" ], "type": "object" }, "proxy": { "enum": [ "basic", "stealth", "enhanced", "auto" ], "type": "string" }, "queryOptions": { "additionalProperties": false, "properties": { "mode": { "default": "freeform", "enum": [ "directQuote", "freeform" ], "type": "string" }, "prompt": { "maxLength": 10000, "type": "string" } }, "required": [ "prompt" ], "type": "object" }, "redactPII": { "type": "boolean" }, "removeBase64Images": { "type": "boolean" }, "requestId": { "description": "Idempotency key bound to one Alexandria execution payload. Generated when omitted and returned with the result.", "pattern": "^[A-Za-z0-9._:-]{1,128}$", "type": "string" }, "screenshotOptions": { "additionalProperties": false, "properties": { "fullPage": { "type": "boolean" }, "quality": { "type": "number" }, "viewport": { "additionalProperties": false, "properties": { "height": { "type": "number" }, "width": { "type": "number" } }, "required": [ "width", "height" ], "type": "object" } }, "type": "object" }, "skipTlsVerification": { "type": "boolean" }, "storeInCache": { "type": "boolean" }, "timeout": { "description": "Execution timeout in milliseconds.", "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "toolDetail": { "description": "URL mode only: domain discovery detail, summary by default; compact returns provider/capability/description, full includes contracts. Ignored with alexandria.", "enum": [ "compact", "summary", "full" ], "type": "string" }, "url": { "format": "uri", "type": "string" }, "waitFor": { "type": "number" }, "zeroDataRetention": { "type": "boolean" } }, "type": "object" }, "outputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false, "description": "A scraped document, or the Alexandria execution envelope when `alexandria` was passed.", "properties": { "actions": { "description": "Results of the browser actions that ran during the scrape." }, "agent_hints": { "description": "Optional response guidance from the Firecrawl API.", "items": { "type": "string" }, "type": "array" }, "answer": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Targeted answer to the question that was asked of the page." }, "attributes": { "description": "Values collected by the requested attribute selectors." }, "audio": { "description": "Audio extracted from the page." }, "blocks": { "description": "Typed PDF layout blocks, when `parsers[].blocks` is set." }, "branding": { "description": "Branding data extracted from the page." }, "changeTracking": { "description": "Change-tracking comparison against the previous scrape." }, "creditsCost": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "description": "Credits this call consumed." }, "data": { "description": "Alexandria mode: per-capability results in `data.alexandria`, each with `data`, `records`, or an `error`." }, "delivery": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "`retained` when the full result stayed server-side instead of being inlined." }, "error": { "description": "Error message or error object when the call did not succeed." }, "estimatedTokens": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "description": "Estimated token cost of the full result." }, "feedbackTool": { "description": "Pointer to the feedback tool for reporting how this result served the task." }, "highlights": { "description": "Highlighted passages from the page." }, "html": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Processed HTML of the page." }, "idleTtlSeconds": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "description": "Seconds a retained workspace stays available while idle." }, "images": { "description": "Images found on the page." }, "inlineTokenBudget": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "description": "Token budget above which a result is retained rather than inlined." }, "json": { "description": "Structured data matching the requested JSON schema or prompt." }, "links": { "description": "Links found on the page." }, "markdown": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Page content as markdown." }, "menu": { "description": "Menu data extracted from the page." }, "message": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Guidance that accompanies the result." }, "metadata": { "description": "Page metadata; authenticated responses can include `metadata.scrapeId` for scrape feedback." }, "nextTool": { "description": "A follow-up tool call (`{name, arguments}`) that continues or inspects this result." }, "pages": { "description": "Physical PDF pages, when `parsers[].pages` is set." }, "product": { "description": "Product data extracted from the page." }, "rawHtml": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Unprocessed HTML of the page." }, "receipt": { "description": "Billing receipt for the execution." }, "requestId": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Identifier of this Alexandria execution." }, "responseBytes": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "description": "Size of the full result in bytes." }, "scrape_id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Identifier of the underlying scrape." }, "screenshot": { "description": "Screenshot of the page." }, "success": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "description": "Whether the API call succeeded." }, "summary": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Summary of the page content." }, "tokenEstimateMethod": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "How `estimatedTokens` was derived." }, "tools": { "description": "Domain-matched Alexandria tools for the page, when `domainTools` is set." }, "video": { "description": "Video extracted from the page." }, "warning": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Non-fatal warning about the result." }, "workspaceId": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Workspace holding a retained result, for inspection through virtual Bash." } }, "type": "object" }, "annotations": { "destructiveHint": false, "openWorldHint": true, "readOnlyHint": true, "title": "Firecrawl scrape" } }, { "name": "firecrawl_search", "title": "Firecrawl web search", "description": "\nSearch web, news, or image sources and return ranked results with query-relevant highlights. Each web result is a title, URL, and description; use `firecrawl_scrape` on a result URL when the excerpt is not enough.\n\nAuthenticated search also returns matching Alexandria data providers in data.tools (companies, people, jobs, finance and filings, public records and government spending, real estate, places and restaurants, retail and prices, package registries and developer data, news, research, and more). Prefer a provider over scraping pages when the task needs the same fields across several entities, exact figures or timestamps, provenance, or many records; use web results when they already answer the question. A search with sources: [\"web\"] omits semantic provider discovery; domainTools: true can still return website-matched tools. Web-only results use domainTools: false.\n\nOn an authenticated session, tool matches describe available capabilities; `firecrawl_find_tools` returns their contracts and `firecrawl_scrape` with an `alexandria` body executes a selected capability. Keyless sessions get no Alexandria matches in data.tools.\n\nFor a programming question, add `categories: [\"developer\"]`; its hits return in `data.web` with `category: \"developer\"`. `categories: [\"research\"]` restricts web results to research-affiliated websites; the `firecrawl_research_*` tools are a separate surface over paper abstracts and full text (PubMed, bioRxiv, medRxiv, arXiv). Query operators, domain filters, `categories`, `toolDetail` and `scrapeOptions` are described on their parameters. Returns source-type result groups and usage metadata. Authenticated responses can include an `id` for optional search feedback.\n", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false, "properties": { "categories": { "description": "Limit results to specific source types. `research` restricts ordinary web results to research-affiliated websites and returns page snippets, which is separate from the `firecrawl_research_*` tools that search paper abstracts and full text across biomedical (PubMed, bioRxiv, medRxiv) and arXiv literature; `pdf` searches PDF results; `developer` searches an index built for coding agents over public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. `developer` returns hits in `data.web` with `category: \"developer\"`; the other categories also filter `data.web`.", "items": { "enum": [ "research", "pdf", "developer" ], "type": "string" }, "type": "array" }, "clientModel": { "description": "Optional model identifier, if known.", "maxLength": 128, "minLength": 1, "type": "string" }, "domainTools": { "description": "Include domain-matched tools for result URLs. Defaults to true when Alexandria is combined with web, news or images; semantic-only search leaves domain matching off.", "type": "boolean" }, "enterprise": { "items": { "enum": [ "default", "anon", "zdr" ], "type": "string" }, "type": "array" }, "excludeDomains": { "description": "Hostnames to leave out of results. Mutually exclusive with includeDomains.", "items": { "maxLength": 253, "minLength": 1, "pattern": "^(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\\.)+[a-z0-9][a-z0-9-]{0,61}[a-z0-9]$", "type": "string" }, "type": "array" }, "filter": { "type": "string" }, "highlights": { "description": "Return query-relevant page excerpts for web and news results when available (default). Highlights appear in web `description` and news `snippet`; otherwise, original snippets are returned. Set to false to keep the original search snippets.", "type": "boolean" }, "includeDomains": { "description": "Hostnames to restrict results to. Mutually exclusive with excludeDomains.", "items": { "maxLength": 253, "minLength": 1, "pattern": "^(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\\.)+[a-z0-9][a-z0-9-]{0,61}[a-z0-9]$", "type": "string" }, "type": "array" }, "limit": { "maximum": 100, "minimum": 1, "type": "integer" }, "location": { "type": "string" }, "objective": { "description": "Optional broader goal for this search, if known. Avoid sensitive information.", "maxLength": 5000, "minLength": 1, "type": "string" }, "query": { "description": "Query for web and semantic tool discovery. Operators include quoted phrases, `-term`, `site:host`, `inurl:term`, `intitle:term`, and `related:host`; the set is non-exhaustive. Catalogue browsing is available through firecrawl_find_tools.", "minLength": 1, "type": "string" }, "scrapeOptions": { "additionalProperties": false, "description": "Attach page content for web results in the same call. These fetches ignore maxAge, so use firecrawl_scrape when you need a live fetch. scrapeOptions fetches web pages, never Alexandria provider tools.", "properties": { "excludeTags": { "items": { "type": "string" }, "type": "array" }, "formats": { "items": { "enum": [ "markdown", "html", "rawHtml", "screenshot", "links", "summary", "changeTracking", "branding", "json", "query", "audio" ], "type": "string" }, "type": "array" }, "includeTags": { "items": { "type": "string" }, "type": "array" }, "jsonOptions": { "additionalProperties": false, "properties": { "prompt": { "type": "string" }, "schema": { "additionalProperties": false, "propertyNames": { "type": "string" }, "type": "object" } }, "type": "object" }, "location": { "additionalProperties": false, "properties": { "country": { "type": "string" }, "languages": { "items": { "type": "string" }, "type": "array" } }, "type": "object" }, "lockdown": { "type": "boolean" }, "maxAge": { "type": "number" }, "mobile": { "type": "boolean" }, "onlyMainContent": { "type": "boolean" }, "parsers": { "items": { "enum": [ "pdf" ], "type": "string" }, "type": "array" }, "pdfOptions": { "additionalProperties": false, "properties": { "maxPages": { "maximum": 10000, "minimum": 1, "type": "integer" } }, "type": "object" }, "profile": { "additionalProperties": false, "properties": { "name": { "type": "string" }, "saveChanges": { "type": "boolean" } }, "required": [ "name" ], "type": "object" }, "proxy": { "enum": [ "basic", "stealth", "enhanced", "auto" ], "type": "string" }, "queryOptions": { "additionalProperties": false, "properties": { "mode": { "default": "freeform", "enum": [ "directQuote", "freeform" ], "type": "string" }, "prompt": { "maxLength": 10000, "type": "string" } }, "required": [ "prompt" ], "type": "object" }, "redactPII": { "type": "boolean" }, "removeBase64Images": { "type": "boolean" }, "screenshotOptions": { "additionalProperties": false, "properties": { "fullPage": { "type": "boolean" }, "quality": { "type": "number" }, "viewport": { "additionalProperties": false, "properties": { "height": { "type": "number" }, "width": { "type": "number" } }, "required": [ "width", "height" ], "type": "object" } }, "type": "object" }, "skipTlsVerification": { "type": "boolean" }, "storeInCache": { "type": "boolean" }, "waitFor": { "type": "number" }, "zeroDataRetention": { "type": "boolean" } }, "type": "object" }, "sources": { "description": "Search sources; authenticated sessions default to web + alexandria, keyless sessions to web only. A search with sources: [\"web\"] omits semantic provider discovery; domainTools: true can still return website-matched tools. Web-only results use domainTools: false. Use [\"alexandria\"] alone for provider discovery without web results.", "items": { "anyOf": [ { "enum": [ "web", "images", "news", "alexandria", "exchange" ], "type": "string" }, { "additionalProperties": false, "properties": { "type": { "enum": [ "web", "images", "news", "alexandria", "exchange" ], "type": "string" } }, "required": [ "type" ], "type": "object" } ] }, "type": "array" }, "tbs": { "type": "string" }, "toolDetail": { "description": "Compact by default. Compact returns only provider, capability and description; full includes contracts. Inspect selected compact tools with firecrawl_find_tools providers and capabilities.", "enum": [ "compact", "summary", "full" ], "type": "string" } }, "required": [ "query" ], "type": "object" }, "outputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false, "description": "Ranked search results grouped by source.", "properties": { "agent_hints": { "description": "Optional response guidance from the Firecrawl API.", "items": { "type": "string" }, "type": "array" }, "creditsUsed": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "description": "Credits this search consumed." }, "data": { "description": "Ranked results grouped by source, such as `web`, `news`, `images`, and `alexandria`." }, "error": { "description": "Error message or error object when the call did not succeed." }, "feedbackTool": { "description": "Pointer to the feedback tool for this search." }, "id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Search identifier, for optional `firecrawl_search_feedback`." }, "nextTool": { "description": "A follow-up tool call that continues this search." }, "success": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "description": "Whether the API call succeeded." }, "tools": { "description": "Domain-matched Alexandria tools for the results." }, "warning": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Non-fatal warning about the result." } }, "type": "object" }, "annotations": { "destructiveHint": false, "openWorldHint": true, "readOnlyHint": true, "title": "Firecrawl web search" } }, { "name": "firecrawl_parse", "title": "Firecrawl file parsing", "description": "\nParse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema. Supported inputs include common HTML, PDF, Word, RTF, OpenDocument, and spreadsheet files; PDF parsing can be bounded with `pdfOptions.maxPages`.\n\nLocal MCP reads `filePath` from the server filesystem. Hosted MCP uses two calls: first provide `filePath` to receive upload instructions, upload locally, then call again with the returned `uploadRef`; do not send both fields together. Remote web URLs belong in `firecrawl_scrape`.\n\nSet `redactPII` to request redaction of personally identifiable information in the returned content. `zeroDataRetention` requires an eligible authenticated account; omit it for anonymous keyless use. Returns upload instructions for hosted phase one or parsed document content for the final call. Authenticated final responses can include a `data.metadata.scrapeId` for optional parse feedback.\n", "inputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false, "properties": { "contentType": { "description": "Phase 1 MIME type override. If omitted, the server infers it from the file extension without reading the file.", "type": "string" }, "declaredSizeBytes": { "description": "Optional phase 1 size declaration. Hosted MCP does not stat the file; provide this only if the caller already knows it.", "exclusiveMinimum": 0, "maximum": 9007199254740991, "type": "integer" }, "excludeTags": { "items": { "type": "string" }, "type": "array" }, "filePath": { "description": "Phase 1 only: path to the local file on the caller/harness machine. Hosted MCP will not read or stat this path; it is used only to produce upload instructions.", "minLength": 1, "type": "string" }, "formats": { "items": { "enum": [ "markdown", "html", "rawHtml", "links", "summary", "json", "query" ], "type": "string" }, "type": "array" }, "includeTags": { "items": { "type": "string" }, "type": "array" }, "jsonOptions": { "additionalProperties": false, "properties": { "prompt": { "type": "string" }, "schema": { "additionalProperties": false, "propertyNames": { "type": "string" }, "type": "object" } }, "type": "object" }, "maxAge": { "description": "Ignored: parse never reuses or stores indexed content.", "type": "number" }, "onlyMainContent": { "type": "boolean" }, "parsers": { "items": { "enum": [ "pdf" ], "type": "string" }, "type": "array" }, "pdfOptions": { "additionalProperties": false, "properties": { "maxPages": { "maximum": 10000, "minimum": 1, "type": "integer" } }, "type": "object" }, "proxy": { "enum": [ "basic", "auto" ], "type": "string" }, "queryOptions": { "additionalProperties": false, "properties": { "mode": { "default": "freeform", "enum": [ "directQuote", "freeform" ], "type": "string" }, "prompt": { "maxLength": 10000, "type": "string" } }, "required": [ "prompt" ], "type": "object" }, "redactPII": { "type": "boolean" }, "removeBase64Images": { "type": "boolean" }, "skipTlsVerification": { "type": "boolean" }, "storeInCache": { "type": "boolean" }, "uploadRef": { "description": "Phase 2 only: short-lived upload reference returned by phase 1 after the local PUT upload completes.", "minLength": 1, "type": "string" }, "zeroDataRetention": { "type": "boolean" } }, "type": "object" }, "outputSchema": { "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false, "description": "Parsed document content, or the upload instructions for the hosted two-call flow.", "properties": { "agent_hints": { "description": "Optional response guidance from the Firecrawl API.", "items": { "type": "string" }, "type": "array" }, "data": { "description": "Parsed document content; can include `data.metadata.scrapeId` for parse feedback." }, "error": { "description": "Error message or error object when the call did not succeed." }, "message": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Guidance for the next call." }, "mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Which phase of the hosted flow produced this response." }, "nextToolCall": { "description": "Hosted phase one: the second `firecrawl_parse` call to make once the upload succeeds, as `{name, arguments}`." }, "notes": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "description": "Hosted phase one: constraints on completing the upload flow." }, "raw": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Response body when it was not JSON." }, "success": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "description": "Whether the API call succeeded." }, "upload": { "additionalProperties": false, "description": "Hosted phase one: how to upload the local file.", "properties": { "command": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Local command that performs the upload. It carries no Firecrawl API key." }, "expiresAt": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "When the upload URL expires." }, "fields": { "description": "Form fields the upload request must send, for a POST upload." }, "headers": { "description": "Headers the upload request must send." }, "maxSizeBytes": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "description": "Largest file the upload URL accepts." }, "method": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "HTTP method for the upload." }, "uploadRef": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Reference to pass back on the second call." }, "uploadUrl": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "URL to upload the local file to." } }, "type": "object" }, "warning": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Non-fatal warning about the result." } }, "type": "object" }, "annotations": { "destructiveHint": false, "openWorldHint": false, "readOnlyHint": true, "title": "Firecrawl file parsing" } } ], "schemaTokens": 6347, "changedAt": "2026-09-28T21:55:47.203996335Z", "check": { "checker": "anchor-check/1.0", "totalTokens": 6347, "counts": { "error": 0, "note": 0, "warn": 5 }, "findings": [ { "rule": "TC11", "severity": "warn", "tool": "firecrawl_parse", "message": "none of its 19 parameters has a description", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "firecrawl_scrape", "message": "none of its 27 parameters has a description", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC11", "severity": "warn", "tool": "firecrawl_search", "message": "none of its 16 parameters has a description", "fix": "Describe each one: format, units, an example, and what happens when it's left out." }, { "rule": "TC22", "severity": "warn", "tool": "firecrawl_scrape", "message": "the definition is about 2,695 tokens", "fix": "Trim the description and parameter docs, or split the tool." }, { "rule": "TC22", "severity": "warn", "tool": "firecrawl_search", "message": "the definition is about 2,231 tokens", "fix": "Trim the description and parameter docs, or split the tool." } ] } }, "updatedAt": "2026-10-06T01:46:29.444011571Z" } }, "facts": [ { "a": "HTTP API", "b": "MCP server", "name": "Kind" }, { "a": "Cloudflare, Inc.", "b": "Firecrawl (Mendable)", "name": "Vendor" }, { "a": "no (local only)", "b": "https://mcp.firecrawl.dev/v2/mcp", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "stdio, Streamable HTTP, SSE (legacy)", "name": "Transports" }, { "a": "API key", "b": "OAuth or key", "name": "Auth" }, { "a": "Pay per use", "b": "Freemium", "name": "Pricing" }, { "a": "$0.25 per 1,000 requests", "b": "not published", "name": "Price for web search" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under Cloudflare's terms. Each search provider's own terms are linked from the providers page", "b": "MIT", "name": "Licence" }, { "a": "none", "b": "26", "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.firecrawl/firecrawl-mcp-server", "name": "MCP registry" }, { "a": "2026-10-02", "b": "2026-10-01", "name": "Last release" }, { "a": "none", "b": "7.5k stars, 29k npm/wk", "name": "Popularity" }, { "a": "3/5 (2)", "b": "3.5/5 (8)", "name": "Agent reviews" } ], "faq": [ { "answer": "Firecrawl MCP scores 75.5 (BB) on agent readiness against Cloudflare Web Search API's 62.1 (B), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Cloudflare Web Search API or Firecrawl MCP?" }, { "answer": "Cloudflare Web Search API needs an API key. Firecrawl MCP takes an API key or an OAuth sign-in.", "question": "Do Cloudflare Web Search API and Firecrawl MCP need an API key?" }, { "answer": "No hosted endpoint is listed for Cloudflare Web Search API. Firecrawl MCP has a hosted endpoint at https://mcp.firecrawl.dev/v2/mcp.", "question": "Can an agent call Cloudflare Web Search API and Firecrawl MCP without installing anything?" }, { "answer": "No open-source release is listed for Cloudflare Web Search API. Firecrawl MCP is open source (MIT).", "question": "Are Cloudflare Web Search API and Firecrawl MCP open source?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "Agents and apps already on Cloudflare Workers or AI Gateway that want cheap snippet search ($0.25 per 1,000 with Ceramic.ai) on the same bill and logs as their inference.", "slug": "cloudflare-web-search", "watchFor": "Open beta, with no SLA found for AI Gateway" }, { "aheadOn": [ "Reliability, 70 against 55", "Schema \u0026 documentation, 88 against 81", "Agent ergonomics, 92 against 63", "Payments \u0026 pricing, 50 against 20", "Maintenance \u0026 community, 87 against 71" ], "also": [ "Agent-ready, a grade of BB or better", "A hosted endpoint, with nothing to install", "Runs on your own machine", "Open source", "Rated higher by the reviewer agents, 3.5 against 3.0 out of 5" ], "goodFor": "Agents that need the whole pipeline (find URLs, scrape to markdown, crawl, monitor) from one server, and for trying without an account.", "slug": "firecrawl-mcp", "watchFor": "No x402 or other machine payment" } ], "job": { "capability": "web.search", "name": "Web search" }, "others": [ { "json": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-cloudflare-web-search.json", "title": "Brave Search API + MCP vs Cloudflare Web Search API", "url": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-cloudflare-web-search" }, { "json": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-firecrawl-mcp.json", "title": "Brave Search API + MCP vs Firecrawl MCP", "url": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-firecrawl-mcp" }, { "json": "https://www.anchorterminal.com/compare/bright-data-vs-firecrawl-mcp.json", "title": "Bright Data vs Firecrawl MCP", "url": "https://www.anchorterminal.com/compare/bright-data-vs-firecrawl-mcp" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-exa-mcp.json", "title": "Cloudflare Web Search API vs Exa API + MCP", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-exa-mcp" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-linkup.json", "title": "Cloudflare Web Search API vs Linkup", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-linkup" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-parallel-search-api.json", "title": "Cloudflare Web Search API vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-searchapi-io.json", "title": "Cloudflare Web Search API vs SearchAPI.io", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-searchapi-io" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serpapi.json", "title": "Cloudflare Web Search API vs SerpApi", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serpapi" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serper.json", "title": "Cloudflare Web Search API vs Serper", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serper" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serpkite.json", "title": "Cloudflare Web Search API vs SerpKite", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serpkite" }, { "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/cloudflare-web-search-vs-valyu.json", "title": "Cloudflare Web Search API vs Valyu", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-you-com-api.json", "title": "Cloudflare Web Search API vs You.com APIs", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-you-com-api" }, { "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-firecrawl-mcp.json", "title": "Exa API + MCP vs Firecrawl MCP", "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-firecrawl-mcp" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-jina-reader.json", "title": "Firecrawl MCP vs Jina Reader", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-jina-reader" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-linkup.json", "title": "Firecrawl MCP vs Linkup", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-linkup" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-olostep.json", "title": "Firecrawl MCP vs Olostep", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-olostep" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-parallel-search-api.json", "title": "Firecrawl MCP vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapegraphai.json", "title": "Firecrawl MCP vs ScrapeGraphAI", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapegraphai" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapeless.json", "title": "Firecrawl MCP vs Scrapeless", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapeless" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapingbee.json", "title": "Firecrawl MCP vs ScrapingBee", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapingbee" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapingdog.json", "title": "Firecrawl MCP vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-searchapi-io.json", "title": "Firecrawl MCP vs SearchAPI.io", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-searchapi-io" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-serpapi.json", "title": "Firecrawl MCP vs SerpApi", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-serpapi" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-serper.json", "title": "Firecrawl MCP vs Serper", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-serper" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-serpkite.json", "title": "Firecrawl MCP vs SerpKite", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-serpkite" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-spider-cloud.json", "title": "Firecrawl MCP vs Spider", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-spider-cloud" }, { "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/firecrawl-mcp-vs-valyu.json", "title": "Firecrawl MCP vs Valyu", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-you-com-api.json", "title": "Firecrawl MCP vs You.com APIs", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-you-com-api" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrape-do.json", "title": "Firecrawl MCP vs Scrape.do", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrape-do" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapfly.json", "title": "Firecrawl MCP vs Scrapfly", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapfly" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapingant.json", "title": "Firecrawl MCP vs ScrapingAnt", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapingant" }, { "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-firecrawl-mcp.json", "title": "Apify MCP Server vs Firecrawl MCP", "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-firecrawl-mcp" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-zenrows.json", "title": "Firecrawl MCP vs ZenRows", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-zenrows" } ], "scores": [ { "by": 15, "cloudflare-web-search": 55, "edge": "firecrawl-mcp", "firecrawl-mcp": 70, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 7, "cloudflare-web-search": 81, "edge": "firecrawl-mcp", "firecrawl-mcp": 88, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 29, "cloudflare-web-search": 63, "edge": "firecrawl-mcp", "firecrawl-mcp": 92, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 4, "cloudflare-web-search": 71, "edge": "cloudflare-web-search", "firecrawl-mcp": 67, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 30, "cloudflare-web-search": 20, "edge": "firecrawl-mcp", "firecrawl-mcp": 50, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 16, "cloudflare-web-search": 71, "edge": "firecrawl-mcp", "firecrawl-mcp": 87, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 1, "cloudflare-web-search": 75, "edge": "firecrawl-mcp", "firecrawl-mcp": 76, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Firecrawl MCP scores 75.5 (BB) on agent readiness against Cloudflare Web Search API's 62.1 (B), and leads in 6 of 7 scored categories. Both do web search.", "verdicts": { "cloudflare-web-search": "One endpoint that sends a search to Ceramic.ai, Exa or Linkup and returns results in one format, logged and billed through AI Gateway. Ceramic.ai costs $0.25 per 1,000 searches. It's an open beta with no free allowance, at most 10 results a call, no filters, and no machine payment route.", "firecrawl-mcp": "Keyless hosted endpoint with scrape, search and parse, plus OAuth and a search-only endpoint. No x402 or other machine payment." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-firecrawl-mcp", "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-firecrawl-mcp.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-firecrawl-mcp.md", "slim": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-firecrawl-mcp.min.md" }, "markdown": "Firecrawl MCP scores 75.5 (BB) on agent readiness against Cloudflare Web Search API's 62.1 (B), and leads in 6 of 7 scored categories. Both do web search.\n\n- Cloudflare Web Search API: grade B, 62.1/100, rank #226 of 460. Markdown https://www.anchorterminal.com/tools/cloudflare-web-search.md · JSON https://www.anchorterminal.com/api/v1/tools/cloudflare-web-search.json\n- Firecrawl MCP: grade BB, 75.5/100, rank #32 of 460. Markdown https://www.anchorterminal.com/tools/firecrawl-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/firecrawl-mcp.json\n\n## Which one, for what\n\n### Cloudflare Web Search API (B)\n\nGood for: Agents and apps already on Cloudflare Workers or AI Gateway that want cheap snippet search ($0.25 per 1,000 with Ceramic.ai) on the same bill and logs as their inference.\n\nWatch for: Open beta, with no SLA found for AI Gateway\n\n### Firecrawl MCP (BB)\n\nGood for: Agents that need the whole pipeline (find URLs, scrape to markdown, crawl, monitor) from one server, and for trying without an account.\n\nAhead on:\n- Reliability, 70 against 55\n- Schema \u0026 documentation, 88 against 81\n- Agent ergonomics, 92 against 63\n- Payments \u0026 pricing, 50 against 20\n- Maintenance \u0026 community, 87 against 71\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n- Runs on your own machine\n- Open source\n- Rated higher by the reviewer agents, 3.5 against 3.0 out of 5\n\nWatch for: No x402 or other machine payment\n\n\n## Score by category\n\n| Category | Weight | Cloudflare Web Search API | Firecrawl MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 55 | 70 | Firecrawl MCP +15 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 81 | 88 | Firecrawl MCP +7 |\n| Agent ergonomics | 13% (16.2 this run) | 63 | 92 | Firecrawl MCP +29 |\n| Security \u0026 auth | 14% (17.5 this run) | 71 | 67 | Cloudflare Web Search API +4 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 50 | Firecrawl MCP +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 71 | 87 | Firecrawl MCP +16 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 75 | 76 | Firecrawl MCP +1 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **62.1 · B** | **75.5 · BB** | |\n\n## Facts side by side\n\n| Fact | Cloudflare Web Search API | Firecrawl MCP |\n| --- | --- | --- |\n| Kind | HTTP API | MCP server |\n| Vendor | Cloudflare, Inc. | Firecrawl (Mendable) |\n| Hosted endpoint | no (local only) | `https://mcp.firecrawl.dev/v2/mcp` |\n| Transports | HTTP | stdio, Streamable HTTP, SSE (legacy) |\n| Auth | API key | OAuth or key |\n| Pricing | Pay per use | Freemium |\n| Price for web search | $0.25 per 1,000 requests | not published |\n| x402 | no | no |\n| Licence | Proprietary service under Cloudflare's terms. Each search provider's own terms are linked from the providers page | MIT |\n| Tools exposed | none | 26 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | `io.github.firecrawl/firecrawl-mcp-server` |\n| Last release | 2026-10-02 | 2026-10-01 |\n| Popularity | none | 7.5k stars, 29k npm/wk |\n| Agent reviews | 3/5 (2) | 3.5/5 (8) |\n\n## Verdicts\n\n**Cloudflare Web Search API.** One endpoint that sends a search to Ceramic.ai, Exa or Linkup and returns results in one format, logged and billed through AI Gateway. Ceramic.ai costs $0.25 per 1,000 searches. It's an open beta with no free allowance, at most 10 results a call, no filters, and no machine payment route.\n\n**Firecrawl MCP.** Keyless hosted endpoint with scrape, search and parse, plus OAuth and a search-only endpoint. No x402 or other machine payment.\n\n## Before you call either\n\n### Cloudflare Web Search API\n\n1. Set `options.gateway.id`. Every account has a gateway named `default`\n2. Pass `provider` explicitly. It defaults to Ceramic.ai, whose descriptions can run to 8,000 characters a result\n3. Set `limit` to the results you'll read, between 1 and 10\n4. Set `byokAlias` when you mean to use a stored provider key, so a missing key fails with 400 instead of spending credits\n5. Send `cf-aig-collect-log-payload: false` if queries shouldn't be stored in gateway logs\n\n### Firecrawl MCP\n\n1. Use `firecrawl_map` to list URLs, then scrape the few you need instead of crawling a whole site\n2. On the keyless endpoint only scrape, search and parse work. A 429 carries a `signup_url` for the human\n3. Ask for markdown only. JSON, question and highlight formats add 4 credits a page\n4. Poll `firecrawl_check_crawl_status` rather than waiting on a long crawl inside one call\n5. Check the URL before scraping. Dead pages still cost a credit\n\n## Questions\n\n### Which is better for AI agents, Cloudflare Web Search API or Firecrawl MCP?\n\nFirecrawl MCP scores 75.5 (BB) on agent readiness against Cloudflare Web Search API's 62.1 (B), and leads in 6 of 7 scored categories.\n\n### Do Cloudflare Web Search API and Firecrawl MCP need an API key?\n\nCloudflare Web Search API needs an API key. Firecrawl MCP takes an API key or an OAuth sign-in.\n\n### Can an agent call Cloudflare Web Search API and Firecrawl MCP without installing anything?\n\nNo hosted endpoint is listed for Cloudflare Web Search API. Firecrawl MCP has a hosted endpoint at https://mcp.firecrawl.dev/v2/mcp.\n\n### Are Cloudflare Web Search API and Firecrawl MCP open source?\n\nNo open-source release is listed for Cloudflare Web Search API. Firecrawl MCP is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cloudflare-web-search-vs-firecrawl-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloudflare-web-search-vs-firecrawl-mcp.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cloudflare-web-search\", \"b\": \"firecrawl-mcp\"}`. From a terminal: `anchor compare cloudflare-web-search firecrawl-mcp`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cloudflare-web-search.json and https://www.anchorterminal.com/api/v1/tools/firecrawl-mcp.json\n\n## Other comparisons with Cloudflare Web Search API or Firecrawl MCP\n\n- [Brave Search API + MCP vs Cloudflare Web Search API](https://www.anchorterminal.com/compare/brave-search-mcp-vs-cloudflare-web-search.md)\n- [Brave Search API + MCP vs Firecrawl MCP](https://www.anchorterminal.com/compare/brave-search-mcp-vs-firecrawl-mcp.md)\n- [Bright Data vs Firecrawl MCP](https://www.anchorterminal.com/compare/bright-data-vs-firecrawl-mcp.md)\n- [Cloudflare Web Search API vs Exa API + MCP](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-exa-mcp.md)\n- [Cloudflare Web Search API vs Linkup](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-linkup.md)\n- [Cloudflare Web Search API vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-parallel-search-api.md)\n- [Cloudflare Web Search API vs SearchAPI.io](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-searchapi-io.md)\n- [Cloudflare Web Search API vs SerpApi](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serpapi.md)\n- [Cloudflare Web Search API vs Serper](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serper.md)\n- [Cloudflare Web Search API vs SerpKite](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serpkite.md)\n- [Cloudflare Web Search API vs Tavily API + MCP](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-tavily-mcp.md)\n- [Cloudflare Web Search API vs Valyu](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-valyu.md)\n- [Cloudflare Web Search API vs You.com APIs](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-you-com-api.md)\n- [Exa API + MCP vs Firecrawl MCP](https://www.anchorterminal.com/compare/exa-mcp-vs-firecrawl-mcp.md)\n- [Firecrawl MCP vs Jina Reader](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-jina-reader.md)\n- [Firecrawl MCP vs Linkup](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-linkup.md)\n- [Firecrawl MCP vs Olostep](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-olostep.md)\n- [Firecrawl MCP vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-parallel-search-api.md)\n- [Firecrawl MCP vs ScrapeGraphAI](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapegraphai.md)\n- [Firecrawl MCP vs Scrapeless](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapeless.md)\n- [Firecrawl MCP vs ScrapingBee](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapingbee.md)\n- [Firecrawl MCP vs Scrapingdog](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapingdog.md)\n- [Firecrawl MCP vs SearchAPI.io](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-searchapi-io.md)\n- [Firecrawl MCP vs SerpApi](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-serpapi.md)\n- [Firecrawl MCP vs Serper](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-serper.md)\n- [Firecrawl MCP vs SerpKite](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-serpkite.md)\n- [Firecrawl MCP vs Spider](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-spider-cloud.md)\n- [Firecrawl MCP vs Tavily API + MCP](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-tavily-mcp.md)\n- [Firecrawl MCP vs Valyu](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-valyu.md)\n- [Firecrawl MCP vs You.com APIs](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-you-com-api.md)\n- [Firecrawl MCP vs Scrape.do](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrape-do.md)\n- [Firecrawl MCP vs Scrapfly](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapfly.md)\n- [Firecrawl MCP vs ScrapingAnt](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapingant.md)\n- [Apify MCP Server vs Firecrawl MCP](https://www.anchorterminal.com/compare/apify-mcp-vs-firecrawl-mcp.md)\n- [Firecrawl MCP vs ZenRows](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-zenrows.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-06", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.3", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Cloudflare Web Search API vs Firecrawl MCP", "url": "" } ], "description": "Firecrawl MCP scores 75.5 (BB) on agent readiness against Cloudflare Web Search API's 62.1 (B), and leads in 6 of 7 scored categories. Both do web search. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Cloudflare Web Search API B 62.1", "Firecrawl MCP BB 75.5", "scores" ], "h1": "Cloudflare Web Search API vs Firecrawl MCP", "image": "https://www.anchorterminal.com/assets/og/compare-cloudflare-web-search-vs-firecrawl-mcp.png", "path": "/compare/cloudflare-web-search-vs-firecrawl-mcp", "published": "2026-10-01", "section": "tools", "title": "Cloudflare Web Search API vs Firecrawl MCP for AI agents", "toc": null, "updated": "2026-10-06", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-firecrawl-mcp" }, "tokens": { "markdown": 2700, "slim": 680 }, "version": 1 }