{
  "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": "Tavily API + MCP scores 77.2 (BB) on agent readiness against Cloudflare Web Search API's 62.1 (B), and leads in 5 of 7 scored categories. Cloudflare Web Search API leads on security \u0026 auth and transparency \u0026 trust.",
    "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": "2026-09-18",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 77.2,
        "grade": "BB",
        "agentReady": true,
        "rank": 17,
        "ranked": true,
        "rankOf": 460,
        "categoryRank": 1,
        "methodology": "0.3",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 81,
          "maintenance": 85,
          "payments": 75,
          "reliability": 90,
          "schema": 89,
          "security": 52,
          "transparency": 65
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-04"
        },
        "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": "0.3",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 77.2
          }
        ],
        "editorialScores": {
          "ergonomics": 81,
          "maintenance": 85,
          "payments": 75,
          "reliability": 90,
          "schema": 89,
          "security": 52,
          "transparency": 47
        },
        "provenanceScore": 82
      },
      "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": "2026-10-04",
        "score": 82
      },
      "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": "2026-10-06T01:46:36.834586125Z",
          "lastOk": true,
          "lastStatus": 200,
          "lastMs": 246,
          "lastNote": "initialize answered",
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 256,
          "p95ms24h": 315,
          "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.tavily.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-10-06T01:47:30.451961901Z"
        },
        "versions": [
          {
            "registry": "mcp-registry",
            "name": "io.github.tavily-ai/tavily-mcp",
            "version": "0.2.15",
            "seenAt": "2026-10-05T23:55:54.568086057Z"
          },
          {
            "registry": "npm",
            "name": "@tavily/core",
            "version": "0.7.13",
            "seenAt": "2026-10-05T17:06:40.488071941Z"
          },
          {
            "registry": "npm",
            "name": "tavily-mcp",
            "version": "0.2.22",
            "seenAt": "2026-10-05T17:06:41.064038866Z"
          },
          {
            "registry": "pypi",
            "name": "tavily-python",
            "version": "0.8.4",
            "released": "2026-09-18",
            "seenAt": "2026-10-05T17:06:40.884172564Z"
          }
        ],
        "githubStars": 2417,
        "npmWeekly": 472271,
        "pypiWeekly": 1688928,
        "securityTxt": {
          "url": "https://tavily.com/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-10-05T15:16:29.366028393Z"
        },
        "llmsTxt": {
          "url": "https://docs.tavily.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-05T15:19:30.831330756Z"
        },
        "domain": {
          "domain": "tavily.com",
          "registered": "2023-04-13",
          "source": "https://rdap.verisign.com/com/v1/domain/tavily.com",
          "checkedAt": "2026-10-04T13:10:11.715455706Z"
        },
        "pages": [
          {
            "url": "https://docs.tavily.com/changelog",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-10-05T15:56:25.208759491Z",
            "changedAt": "2026-10-01T13:13:02.472584343Z",
            "fingerprint": "b80e278c1058"
          },
          {
            "url": "https://www.tavily.com/pricing",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-10-05T16:04:43.357845627Z",
            "changedAt": "2026-10-01T13:18:40.634970947Z",
            "fingerprint": "a7eb93565f03"
          },
          {
            "url": "https://www.tavily.com/privacy",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-10-05T16:04:45.493102543Z",
            "changedAt": "2026-10-01T13:18:42.856868801Z",
            "fingerprint": "7d1afba1cbc9"
          },
          {
            "url": "https://www.tavily.com/terms",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-10-05T16:04:47.508197448Z",
            "changedAt": "2026-10-01T13:18:44.802104507Z",
            "fingerprint": "14aecf61290a"
          }
        ],
        "mcpTools": {
          "url": "https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e",
          "checkedAt": "2026-10-05T22:31:13.867565617Z",
          "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. Returns snippets and source URLs.",
              "inputSchema": {
                "additionalProperties": false,
                "properties": {
                  "country": {
                    "default": "",
                    "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.",
                    "type": "string"
                  },
                  "end_date": {
                    "default": "",
                    "description": "Will return all results before the specified end date. Required to be written in the format YYYY-MM-DD",
                    "type": "string"
                  },
                  "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": {
                    "default": [],
                    "description": "List of domains to specifically exclude, if the user asks to exclude a domain set this to the domain of the site",
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  },
                  "include_domains": {
                    "default": [],
                    "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",
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  },
                  "include_favicon": {
                    "default": false,
                    "description": "Whether to include the favicon URL for each result",
                    "type": "boolean"
                  },
                  "include_image_descriptions": {
                    "default": false,
                    "description": "Include a list of query-related images and their descriptions in the response",
                    "type": "boolean"
                  },
                  "include_images": {
                    "default": false,
                    "description": "Include a list of query-related images in the response",
                    "type": "boolean"
                  },
                  "include_raw_content": {
                    "default": false,
                    "description": "Include the cleaned and parsed HTML content of each search result",
                    "type": "boolean"
                  },
                  "max_results": {
                    "default": 5,
                    "description": "The maximum number of search results to return",
                    "type": "integer"
                  },
                  "query": {
                    "description": "Search query",
                    "type": "string"
                  },
                  "search_depth": {
                    "default": "basic",
                    "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",
                    "enum": [
                      "basic",
                      "advanced",
                      "fast",
                      "ultra-fast"
                    ],
                    "type": "string"
                  },
                  "start_date": {
                    "default": "",
                    "description": "Will return all results after the specified start date. Required to be written in the format YYYY-MM-DD.",
                    "type": "string"
                  },
                  "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"
                  },
                  "topic": {
                    "const": "general",
                    "default": "general",
                    "description": "The category of the search. This will determine which of our agents will be used for the search",
                    "type": "string"
                  }
                },
                "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.",
              "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"
                  },
                  "query": {
                    "default": "",
                    "description": "Query to rerank content chunks by relevance",
                    "type": "string"
                  },
                  "urls": {
                    "description": "List of URLs to extract content from",
                    "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"
                  },
                  "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"
                  },
                  "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"
                  },
                  "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": {
                  "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": 2262,
          "changedAt": "2026-09-28T21:55:54.996628221Z",
          "check": {
            "checker": "anchor-check/1.0",
            "totalTokens": 2262,
            "counts": {
              "error": 0,
              "note": 0,
              "warn": 1
            },
            "findings": [
              {
                "rule": "TC14",
                "severity": "warn",
                "tool": "tavily_search",
                "message": "allowed values are in the description, not an enum: country",
                "fix": "Move them into enum."
              }
            ]
          }
        },
        "updatedAt": "2026-10-06T01:47:30.451961901Z"
      }
    },
    "facts": [
      {
        "a": "HTTP API",
        "b": "MCP server",
        "name": "Kind"
      },
      {
        "a": "Cloudflare, Inc.",
        "b": "Tavily",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP",
        "b": "stdio, Streamable HTTP, HTTP",
        "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": "$7.50 per 1,000 requests",
        "name": "Price for web search"
      },
      {
        "a": "no",
        "b": "payer tooling only",
        "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": "5",
        "name": "Tools exposed"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "not listed",
        "b": "io.github.tavily-ai/tavily-mcp",
        "name": "MCP registry"
      },
      {
        "a": "2026-10-02",
        "b": "2026-09-18",
        "name": "Last release"
      },
      {
        "a": "none",
        "b": "2.4k stars, 452k npm/wk, 1.6M PyPI/wk",
        "name": "Popularity"
      },
      {
        "a": "3/5 (2)",
        "b": "3.6/5 (8)",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Tavily API + MCP scores 77.2 (BB) on agent readiness against Cloudflare Web Search API's 62.1 (B), and leads in 5 of 7 scored categories. Cloudflare Web Search API leads on security \u0026 auth and transparency \u0026 trust.",
        "question": "Which is better for AI agents, Cloudflare Web Search API or Tavily API + MCP?"
      },
      {
        "answer": "Cloudflare Web Search API, at $0.25 per 1,000 requests against $7.50 per 1,000 requests for Tavily API + MCP. These are the vendors' published prices for the job.",
        "question": "Which is cheaper for web search, Cloudflare Web Search API or Tavily API + MCP?"
      },
      {
        "answer": "Cloudflare Web Search API needs an API key. Tavily API + MCP takes an API key or an OAuth sign-in.",
        "question": "Do Cloudflare Web Search API and Tavily API + MCP need an API key?"
      },
      {
        "answer": "No hosted endpoint is listed for Cloudflare Web Search API. Tavily API + MCP has a hosted endpoint at https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e.",
        "question": "Can an agent call Cloudflare Web Search API and Tavily API + MCP without installing anything?"
      },
      {
        "answer": "No open-source release is listed for Cloudflare Web Search API. Tavily API + MCP is open source (MIT).",
        "question": "Are Cloudflare Web Search API and Tavily API + MCP open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Security \u0026 auth, 71 against 52",
          "Transparency \u0026 trust, 75 against 65"
        ],
        "also": [
          "Cheaper for web search, $0.25 against $7.50 per 1,000 requests"
        ],
        "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, 90 against 55",
          "Schema \u0026 documentation, 89 against 81",
          "Agent ergonomics, 81 against 63",
          "Payments \u0026 pricing, 75 against 20",
          "Maintenance \u0026 community, 85 against 71"
        ],
        "also": [
          "Agent-ready, a grade of BB or better",
          "A hosted endpoint, with nothing to install",
          "Runs on your own machine",
          "Free to start without a card",
          "Open source"
        ],
        "goodFor": "An agent that needs search plus page text in one call and has no account yet.",
        "slug": "tavily-mcp",
        "watchFor": "x402 covers advanced search only, not extract, map, crawl or research"
      }
    ],
    "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-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-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-firecrawl-mcp.json",
        "title": "Cloudflare Web Search API vs Firecrawl MCP",
        "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-firecrawl-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-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-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/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-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/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": [
      {
        "by": 35,
        "cloudflare-web-search": 55,
        "edge": "tavily-mcp",
        "key": "reliability",
        "name": "Reliability",
        "tavily-mcp": 90,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 8,
        "cloudflare-web-search": 81,
        "edge": "tavily-mcp",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "tavily-mcp": 89,
        "weight": 13
      },
      {
        "by": 18,
        "cloudflare-web-search": 63,
        "edge": "tavily-mcp",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "tavily-mcp": 81,
        "weight": 13
      },
      {
        "by": 19,
        "cloudflare-web-search": 71,
        "edge": "cloudflare-web-search",
        "key": "security",
        "name": "Security \u0026 auth",
        "tavily-mcp": 52,
        "weight": 14
      },
      {
        "by": 55,
        "cloudflare-web-search": 20,
        "edge": "tavily-mcp",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "tavily-mcp": 75,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 14,
        "cloudflare-web-search": 71,
        "edge": "tavily-mcp",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "tavily-mcp": 85,
        "weight": 7
      },
      {
        "by": 10,
        "cloudflare-web-search": 75,
        "edge": "cloudflare-web-search",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "tavily-mcp": 65,
        "weight": 7
      }
    ],
    "summary": "Tavily API + MCP scores 77.2 (BB) on agent readiness against Cloudflare Web Search API's 62.1 (B), and leads in 5 of 7 scored categories. Cloudflare Web Search API leads on security \u0026 auth and transparency \u0026 trust. Both do web search. Cloudflare Web Search API is cheaper for web search, $0.25 against $7.50 per 1,000 requests.",
    "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.",
      "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/cloudflare-web-search-vs-tavily-mcp",
    "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-tavily-mcp.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-tavily-mcp.md",
    "slim": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-tavily-mcp.min.md"
  },
  "markdown": "Tavily API + MCP scores 77.2 (BB) on agent readiness against Cloudflare Web Search API's 62.1 (B), and leads in 5 of 7 scored categories. Cloudflare Web Search API leads on security \u0026 auth and transparency \u0026 trust. Both do web search. Cloudflare Web Search API is cheaper for web search, $0.25 against $7.50 per 1,000 requests.\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- Tavily API + MCP: grade BB, 77.2/100, rank #17 of 460. Markdown https://www.anchorterminal.com/tools/tavily-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/tavily-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\nAhead on:\n- Security \u0026 auth, 71 against 52\n- Transparency \u0026 trust, 75 against 65\n\nAlso in its favour:\n- Cheaper for web search, $0.25 against $7.50 per 1,000 requests\n\nWatch for: Open beta, with no SLA found for AI Gateway\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 55\n- Schema \u0026 documentation, 89 against 81\n- Agent ergonomics, 81 against 63\n- Payments \u0026 pricing, 75 against 20\n- Maintenance \u0026 community, 85 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- Free to start without a card\n- Open source\n\nWatch for: x402 covers advanced search only, not extract, map, crawl or research\n\n\n## Score by category\n\n| Category | Weight | Cloudflare Web Search API | Tavily API + MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 55 | 90 | Tavily API + MCP +35 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 81 | 89 | Tavily API + MCP +8 |\n| Agent ergonomics | 13% (16.2 this run) | 63 | 81 | Tavily API + MCP +18 |\n| Security \u0026 auth | 14% (17.5 this run) | 71 | 52 | Cloudflare Web Search API +19 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 75 | Tavily API + MCP +55 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 71 | 85 | Tavily API + MCP +14 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 75 | 65 | Cloudflare Web Search API +10 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **62.1 · B** | **77.2 · BB** | |\n\n## Facts side by side\n\n| Fact | Cloudflare Web Search API | Tavily API + MCP |\n| --- | --- | --- |\n| Kind | HTTP API | MCP server |\n| Vendor | Cloudflare, Inc. | Tavily |\n| Hosted endpoint | no (local only) | `https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e` |\n| Transports | HTTP | stdio, Streamable HTTP, HTTP |\n| Auth | API key | OAuth or key |\n| Pricing | Pay per use | Freemium |\n| Price for web search | $0.25 per 1,000 requests | $7.50 per 1,000 requests |\n| x402 | no | payer tooling only |\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 | 5 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | `io.github.tavily-ai/tavily-mcp` |\n| Last release | 2026-10-02 | 2026-09-18 |\n| Popularity | none | 2.4k stars, 452k npm/wk, 1.6M PyPI/wk |\n| Agent reviews | 3/5 (2) | 3.6/5 (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**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### 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### 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, Cloudflare Web Search API or Tavily API + MCP?\n\nTavily API + MCP scores 77.2 (BB) on agent readiness against Cloudflare Web Search API's 62.1 (B), and leads in 5 of 7 scored categories. Cloudflare Web Search API leads on security \u0026 auth and transparency \u0026 trust.\n\n### Which is cheaper for web search, Cloudflare Web Search API or Tavily API + MCP?\n\nCloudflare Web Search API, at $0.25 per 1,000 requests against $7.50 per 1,000 requests for Tavily API + MCP. These are the vendors' published prices for the job.\n\n### Do Cloudflare Web Search API and Tavily API + MCP need an API key?\n\nCloudflare Web Search API needs an API key. Tavily API + MCP takes an API key or an OAuth sign-in.\n\n### Can an agent call Cloudflare Web Search API and Tavily API + MCP without installing anything?\n\nNo hosted endpoint is listed for Cloudflare Web Search API. Tavily API + MCP has a hosted endpoint at https://mcp.tavily.com/mcp/?tavilyApiKey=\u003ckey\u003e.\n\n### Are Cloudflare Web Search API and Tavily API + MCP open source?\n\nNo open-source release is listed for Cloudflare Web Search API. Tavily API + 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-tavily-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloudflare-web-search-vs-tavily-mcp.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cloudflare-web-search\", \"b\": \"tavily-mcp\"}`. From a terminal: `anchor compare cloudflare-web-search tavily-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/tavily-mcp.json\n\n## Other comparisons with Cloudflare Web Search API or Tavily API + 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 Tavily API + MCP](https://www.anchorterminal.com/compare/brave-search-mcp-vs-tavily-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 Firecrawl MCP](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-firecrawl-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 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 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- [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 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- [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)",
    "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 Tavily API + MCP",
        "url": ""
      }
    ],
    "description": "Tavily API + MCP scores 77.2 (BB) on agent readiness against Cloudflare Web Search API's 62.1 (B), and leads in 5 of 7 scored categories. Cloudflare Web Search API leads on security \u0026 auth and transparency \u0026 trust. Both do web search. Cloudflare Web Search API is cheaper for web…",
    "facts": [
      "Cloudflare Web Search API B 62.1",
      "Tavily API + MCP BB 77.2",
      "scores"
    ],
    "h1": "Cloudflare Web Search API vs Tavily API + MCP",
    "image": "https://www.anchorterminal.com/assets/og/compare-cloudflare-web-search-vs-tavily-mcp.png",
    "path": "/compare/cloudflare-web-search-vs-tavily-mcp",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Cloudflare Web Search API vs Tavily API + MCP for AI agents",
    "toc": null,
    "updated": "2026-10-06",
    "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-tavily-mcp"
  },
  "tokens": {
    "markdown": 2600,
    "slim": 780
  },
  "version": 1
}