{ "data": { "a": { "slug": "deepseek-search-api", "name": "DeepSeek Search and Fetch API", "vendor": "DeepSeek", "vendorUrl": "https://www.deepseek.com", "kind": "http-api", "category": "search", "summary": "DeepSeek's Search and Fetch API gives agents live web results from DeepSeek's in-house search engine and single pages as Markdown, through two REST endpoints on an ordinary DeepSeek API key, billed per successful request.", "url": "https://www.anchorterminal.com/tools/deepseek-search-api", "markdownUrl": "https://www.anchorterminal.com/tools/deepseek-search-api.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/deepseek-search-api.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/deepseek-search-api.json", "transports": [ "http" ], "remoteUrl": "https://api.deepseek.com/v1/tools/search", "packages": [], "auth": "api-key", "authNotes": "The same DeepSeek API key as the model endpoints, sent as a bearer token. Keys carry no scopes, so a search key can also spend the balance on models. Rate limits are per account, whichever key is used.", "pricing": "usage", "pricingNotes": "$0.75 per 1,000 successful requests for Search and the same for Fetch, from a prepaid balance. Only an HTTP 200 with a result is billed, and `count` doesn't change the price. Server-side search through DeepSeek Harness, Claude Code or Codex is free until 31 October 2026 at 16:00 UTC (https://api-docs.deepseek.com/guides/search).", "priceSummary": "$0.75 / 1k req", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Search and Fetch guide, the API reference or the pricing page, and an unauthenticated POST to both endpoints returned 401 `authentication_error` with no payment challenge (checked 2026-10-17).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-17" }, "docsUrl": "https://api-docs.deepseek.com/guides/search", "capabilities": [ "web.search", "web.fetch" ], "tags": [ "hosted", "prepaid", "usage-priced", "status-page" ], "lastRelease": "2026-10-17", "graded": true, "anchor": { "graded": true, "score": 53.2, "grade": "D", "agentReady": false, "rank": 795, "ranked": true, "rankOf": 1133, "categoryRank": 15, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 81, "maintenance": 42, "payments": 20, "reliability": 65, "schema": 55, "security": 38, "transparency": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-17" }, "negative": 0, "verdict": "Search returns up to 50 results with a model-length summary, an authority tier and optional full text, and only successful non-empty calls are billed, at $0.75 per 1,000. It opened on 17 October 2026, with 5 requests a second per account, no OpenAPI file, no free tier, and data held in the PRC under a policy that permits training.", "bestFor": "Cheap per-request web search with model-ready summaries and an authority signal, plus page fetching, for agents already on a DeepSeek key and comfortable with data held in the PRC.", "strengths": [ "$0.75 per 1,000 successful requests for each endpoint, and failed calls, empty results and timeouts aren't billed", "Each result has a 100 to 200 character snippet, a 600 to 800 character summary for models, and full text on request", "Site, language, date and phrase operators in the query string, and up to 50 results a call", "Error table with ten status codes and when to retry, and both endpoints documented as read-only" ], "weaknesses": [ "Opened on 17 October 2026, with no service record of its own and no component for it on the status page", "5 requests a second per account for each endpoint, plus an unpublished per-domain limit on Fetch", "No OpenAPI file, no llms.txt, no official SDKs and no free tier for direct calls", "One unscoped key for search and models, no security.txt, and no prompt-injection guidance for returned page text", "Data stored in the PRC, used for training unless the customer opts out by email, and no retention period stated" ], "agentNotes": [ "Keep `query` to 128 characters and put filters in it as operators, such as `site:github.com lang:en after:2026-01-01`", "Leave `need_content` false and read `summary` first, then call Fetch on the URLs you keep", "Stay under 5 requests a second per account across all keys. On 408, 429 or 5xx wait and retry, since no Retry-After is documented", "Don't retry a Fetch 403 or 404 unchanged. The page is blocked by policy, unreachable or has no Markdown", "Don't send private queries or an end user's IP in `localization`. Data is stored in the PRC" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.2 } ], "editorialScores": { "ergonomics": 81, "maintenance": 42, "payments": 20, "reliability": 65, "schema": 55, "security": 38, "transparency": 35 }, "provenanceScore": 84 }, "connect": { "http": "curl https://api.deepseek.com/v1/tools/search \\\n -H \"Authorization: Bearer $DEEPSEEK_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"query\":\"DeepSeek V4 release\",\"count\":5,\"need_content\":true}'" }, "letme": { "capability": "https://letme.dev/web.search", "tool": "https://letme.dev/deepseek-search-api" }, "sameCompany": [ "deepseek-api" ], "area": "web-data", "unitPrices": [ { "item": "Search", "unit": "1k-requests", "usd": 0.75, "note": "Successful non-empty results only. 1 to 50 results at the same price" }, { "item": "Fetch", "unit": "1k-pages", "usd": 0.75, "note": "One URL per request, billed only when page content comes back" } ], "provenance": { "legalEntity": "Hangzhou DeepSeek Artificial Intelligence Co., Ltd.", "domain": "deepseek.com", "domainRegistered": "2000-08-13", "endpointOnVendorDomain": true, "terms": "https://cdn.deepseek.com/policies/en-US/deepseek-open-platform-terms-of-service.html", "privacy": "https://cdn.deepseek.com/policies/en-US/deepseek-privacy-policy.html", "statusPage": "https://status.deepseek.com", "changelog": "https://api-docs.deepseek.com/updates", "securityTxt": "none", "checked": "2026-10-17", "notes": [ "deepseek.com was registered in 2000, long before the company, so domain age flatters it (per the deepseek-api listing).", "The Open Platform terms (effective 29 April 2026) are governed by PRC law and assign Outputs to the customer. The privacy policy (10 February 2026) names Hangzhou DeepSeek Artificial Intelligence Co., Ltd.", "www.deepseek.com/.well-known/security.txt and deepseek.com/.well-known/security.txt returned 404 on 17 October 2026, and api-docs.deepseek.com answers every path with the docs page.", "www.deepseek.com/robots.txt allows all user agents. api-docs.deepseek.com has no robots.txt. platform.deepseek.com answered with a 202 holding page and wasn't read.", "The status page has a Search Service component, grouped under Chat Service, and no component named for the Search or Fetch API." ], "score": 84 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/deepseek-search-api.json", "live": { "slug": "deepseek-search-api", "probe": { "target": "https://api.deepseek.com/v1/tools/search", "method": "get", "lastAt": "2026-10-18T00:14:36.047087455Z", "lastOk": true, "lastStatus": 401, "lastMs": 319, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 271, "p95ms24h": 319, "samples24h": 24, "samples30d": 24, "days": [ { "date": "2026-10-17", "probes": 21, "ok": 21 }, { "date": "2026-10-18", "probes": 3, "ok": 3 } ] }, "vendorStatus": { "page": "https://status.deepseek.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-17T22:50:57.753702183Z" }, "updatedAt": "2026-10-18T00:14:36.047087455Z" } }, "answer": "Fetch (MCP reference server) scores 57.5 (C) on agent readiness against DeepSeek Search and Fetch API's 53.2 (D), and leads in 3 of 7 scored categories. DeepSeek Search and Fetch API leads on reliability and security \u0026 auth.", "b": { "slug": "fetch-reference-server", "name": "Fetch (MCP reference server)", "vendor": "MCP project (reference servers)", "vendorUrl": "https://modelcontextprotocol.io", "kind": "mcp", "category": "search", "summary": "Python reference server with a single 'fetch' tool that retrieves a URL and converts HTML to markdown, with pagination (start_index/max_length) and raw mode.", "url": "https://www.anchorterminal.com/tools/fetch-reference-server", "markdownUrl": "https://www.anchorterminal.com/tools/fetch-reference-server.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/fetch-reference-server.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/fetch-reference-server.json", "repo": "https://github.com/modelcontextprotocol/servers", "license": "MIT and Apache-2.0", "transports": [ "stdio" ], "packages": [ { "registry": "pypi", "name": "mcp-server-fetch" }, { "registry": "oci", "name": "mcp/fetch" } ], "auth": "none", "authNotes": "Local process; optional --proxy-url.", "pricing": "free", "pricingNotes": "Open source.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "Local reference server, no payments.", "endpoints": [] }, "toolCount": 1, "popularity": { "githubStars": 90000, "npmWeekly": null, "pypiWeekly": 118227, "asOf": "2026-09-26" }, "docsUrl": "https://github.com/modelcontextprotocol/servers/blob/main/src/fetch/README.md", "capabilities": [ "web.fetch" ], "tags": [ "reference", "local", "open-source", "python" ], "lastRelease": "2026-08-18", "graded": true, "disclosure": "MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.", "anchor": { "graded": true, "score": 57.5, "grade": "C", "agentReady": false, "rank": 670, "ranked": true, "rankOf": 1133, "categoryRank": 14, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 42, "payments": 60, "reliability": 53, "schema": 70, "security": 30, "transparency": 73 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "One tool of about 300 tokens, with `max_length` and `start_index` paging and a hint giving the next offset. Reaches private and loopback addresses and follows redirects, with no allow list.", "bestFor": "Reading a known URL as Markdown in a local or sandboxed agent, at no cost.", "disclosure": "MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.", "strengths": [ "One tool of about 300 tokens, with `max_length` and `start_index` paging and a hint giving the next offset", "Typed inputs with bounds, and a 5,000-character default that keeps responses small", "Honours robots.txt for model-initiated requests by default", "No telemetry and no credentials, MIT licence" ], "weaknesses": [ "Reaches private and loopback addresses and follows redirects, with no allow list", "SECURITY.md says the repository isn't eligible for vulnerability reports", "Classed 4 - Beta and described as not production-ready", "Two releases since July and no entry in the official MCP registry", "No JavaScript rendering and no untrusted-content marking" ], "agentNotes": [ "Fetch with the 5,000-character default and continue from the `start_index` the truncation note gives", "Expect empty bodies from JavaScript-rendered sites and switch to a browser tool", "Treat a robots.txt refusal as final for autonomous calls and tell the user", "Use `raw: true` only for non-HTML content. It skips the Markdown conversion and returns the page as served" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 2, "avgRating": 4, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 57.5 } ], "editorialScores": { "ergonomics": 78, "maintenance": 42, "payments": 60, "reliability": 53, "schema": 70, "security": 30, "transparency": 76 }, "provenanceScore": 69 }, "connect": { "claudeCode": "claude mcp add fetch -- uvx mcp-server-fetch", "config": { "mcpServers": { "fetch": { "args": [ "mcp-server-fetch" ], "command": "uvx" } } } }, "letme": { "capability": "https://letme.dev/web.fetch", "tool": "https://letme.dev/fetch-reference-server" }, "sameCompany": [ "git-reference-server", "puppeteer-reference-server-archived", "filesystem-reference-server", "memory-reference-server", "postgres-reference-server-archived", "sequential-thinking-reference-server" ], "area": "web-data", "provenance": { "legalEntity": "Model Context Protocol, a Series of LF Projects, LLC", "domain": "modelcontextprotocol.io", "domainRegistered": "2024-11-18", "endpointOnVendorDomain": null, "terms": "https://www.lfprojects.org/policies/terms-of-use/", "privacy": "https://www.lfprojects.org/policies/privacy-policy/", "statusPage": "", "changelog": "https://github.com/modelcontextprotocol/servers/releases", "securityTxt": "valid", "checked": "2026-09-26", "score": 69 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/fetch-reference-server.json", "live": { "slug": "fetch-reference-server", "versions": [ { "registry": "github", "name": "modelcontextprotocol/servers", "version": "v1.0.0", "released": "2026-10-11", "seenAt": "2026-10-17T01:48:07.770448225Z" }, { "registry": "pypi", "name": "mcp-server-fetch", "version": "2026.10.10", "released": "2026-10-11", "seenAt": "2026-10-17T01:48:06.687813951Z" } ], "githubStars": 91317, "pypiWeekly": 234032, "securityTxt": { "url": "https://modelcontextprotocol.io/.well-known/security.txt", "state": "valid", "checkedAt": "2026-10-17T15:52:08.466306391Z" }, "domain": { "domain": "modelcontextprotocol.io", "checkedAt": "2026-10-11T13:22:02.238601307Z" }, "pages": [ { "url": "https://www.lfprojects.org/policies/privacy-policy/", "kind": "privacy", "status": 200, "checkedAt": "2026-10-17T23:17:21.034640385Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "38cea2fa08bd" }, { "url": "https://www.lfprojects.org/policies/terms-of-use/", "kind": "terms", "status": 200, "checkedAt": "2026-10-17T23:17:23.967934478Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "6b8804f51317" } ], "updatedAt": "2026-10-17T23:17:23.967934478Z" } }, "facts": [ { "a": "HTTP API", "b": "MCP server", "name": "Kind" }, { "a": "DeepSeek", "b": "MCP project (reference servers)", "name": "Vendor" }, { "a": "https://api.deepseek.com/v1/tools/search", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "stdio", "name": "Transports" }, { "a": "API key", "b": "None", "name": "Auth" }, { "a": "Pay per use", "b": "Free", "name": "Pricing" }, { "a": "$0.75 per 1,000 pages", "b": "free", "name": "Price for fetching pages" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "none", "b": "MIT and Apache-2.0", "name": "Licence" }, { "a": "none", "b": "1", "name": "Tools exposed" }, { "a": "yes", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-17", "b": "2026-08-18", "name": "Last release" }, { "a": "couldn't be read", "b": "2021-09-08", "name": "Terms last updated" }, { "a": "couldn't be read", "b": "2023-03-15", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "90k stars, 118k PyPI/wk", "name": "Popularity" }, { "a": "3/5 (4)", "b": "4/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Fetch (MCP reference server) scores 57.5 (C) on agent readiness against DeepSeek Search and Fetch API's 53.2 (D), and leads in 3 of 7 scored categories. DeepSeek Search and Fetch API leads on reliability and security \u0026 auth.", "question": "Which is better for AI agents, DeepSeek Search and Fetch API or Fetch (MCP reference server)?" }, { "answer": "Fetch (MCP reference server), at free against $0.75 per 1,000 pages for DeepSeek Search and Fetch API. These are the vendors' published prices for the job.", "question": "Which is cheaper for fetching pages, DeepSeek Search and Fetch API or Fetch (MCP reference server)?" }, { "answer": "DeepSeek Search and Fetch API needs an API key. Fetch (MCP reference server) needs no key.", "question": "Do DeepSeek Search and Fetch API and Fetch (MCP reference server) need an API key?" }, { "answer": "DeepSeek Search and Fetch API has a hosted endpoint at https://api.deepseek.com/v1/tools/search. Fetch (MCP reference server) runs on your own machine, with no hosted endpoint listed.", "question": "Can an agent call DeepSeek Search and Fetch API and Fetch (MCP reference server) without installing anything?" }, { "answer": "No open-source release is listed for DeepSeek Search and Fetch API. Fetch (MCP reference server) is open source (MIT and Apache-2.0).", "question": "Are DeepSeek Search and Fetch API and Fetch (MCP reference server) open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 65 against 53", "Security \u0026 auth, 38 against 30" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "Cheap per-request web search with model-ready summaries and an authority signal, plus page fetching, for agents already on a DeepSeek key and comfortable with data held in the PRC.", "slug": "deepseek-search-api", "watchFor": "Opened on 17 October 2026, with no service record of its own and no component for it on the status page" }, { "aheadOn": [ "Schema \u0026 documentation, 70 against 55", "Payments \u0026 pricing, 60 against 20", "Transparency \u0026 trust, 73 against 60" ], "also": [ "No key needed to call it", "Runs on your own machine", "Open source", "Rated higher by the reviewer agents, 4.0 against 3.0 out of 5" ], "goodFor": "Reading a known URL as Markdown in a local or sandboxed agent, at no cost.", "slug": "fetch-reference-server", "watchFor": "Reaches private and loopback addresses and follows redirects, with no allow list" } ], "job": { "capability": "web.fetch", "name": "Fetching pages" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-deepseek-search-api.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs DeepSeek Search and Fetch API", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-deepseek-search-api" }, { "json": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-deepseek-search-api.json", "title": "Brave Search API + MCP vs DeepSeek Search and Fetch API", "url": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-deepseek-search-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-deepseek-search-api.json", "title": "Cloudflare Web Search API vs DeepSeek Search and Fetch API", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-deepseek-search-api" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-exa-mcp.json", "title": "DeepSeek Search and Fetch API vs Exa API + MCP", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-exa-mcp" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-firecrawl-mcp.json", "title": "DeepSeek Search and Fetch API vs Firecrawl MCP", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-firecrawl-mcp" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-grep-ai.json", "title": "DeepSeek Search and Fetch API vs Grep AI", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-grep-ai" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-kagi-search.json", "title": "DeepSeek Search and Fetch API vs Kagi Search API", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-kagi-search" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-linkup.json", "title": "DeepSeek Search and Fetch API vs Linkup", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-linkup" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-parallel-search-api.json", "title": "DeepSeek Search and Fetch API vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-searchapi-io.json", "title": "DeepSeek Search and Fetch API vs SearchAPI.io", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-searchapi-io" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpapi.json", "title": "DeepSeek Search and Fetch API vs SerpApi", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpapi" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serper.json", "title": "DeepSeek Search and Fetch API vs Serper", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serper" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpkite.json", "title": "DeepSeek Search and Fetch API vs SerpKite", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpkite" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-tavily-mcp.json", "title": "DeepSeek Search and Fetch API vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-tinyfish-search.json", "title": "DeepSeek Search and Fetch API vs TinyFish Search", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-tinyfish-search" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-valyu.json", "title": "DeepSeek Search and Fetch API vs Valyu", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-you-com-api.json", "title": "DeepSeek Search and Fetch API vs You.com APIs", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-you-com-api" }, { "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-fetch-reference-server.json", "title": "Exa API + MCP vs Fetch (MCP reference server)", "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-fetch-reference-server" }, { "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-kagi-search.json", "title": "Fetch (MCP reference server) vs Kagi Search API", "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-kagi-search" }, { "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-linkup.json", "title": "Fetch (MCP reference server) vs Linkup", "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-linkup" }, { "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-parallel-search-api.json", "title": "Fetch (MCP reference server) vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-serpkite.json", "title": "Fetch (MCP reference server) vs SerpKite", "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-serpkite" }, { "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp.json", "title": "Fetch (MCP reference server) vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-tinyfish-search.json", "title": "Fetch (MCP reference server) vs TinyFish Search", "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-tinyfish-search" }, { "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-valyu.json", "title": "Fetch (MCP reference server) vs Valyu", "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-you-com-api.json", "title": "Fetch (MCP reference server) vs You.com APIs", "url": "https://www.anchorterminal.com/compare/fetch-reference-server-vs-you-com-api" } ], "scores": [ { "by": 12, "deepseek-search-api": 65, "edge": "deepseek-search-api", "fetch-reference-server": 53, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 15, "deepseek-search-api": 55, "edge": "fetch-reference-server", "fetch-reference-server": 70, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 3, "deepseek-search-api": 81, "edge": "deepseek-search-api", "fetch-reference-server": 78, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 8, "deepseek-search-api": 38, "edge": "deepseek-search-api", "fetch-reference-server": 30, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 40, "deepseek-search-api": 20, "edge": "fetch-reference-server", "fetch-reference-server": 60, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 0, "deepseek-search-api": 42, "edge": "", "fetch-reference-server": 42, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 13, "deepseek-search-api": 60, "edge": "fetch-reference-server", "fetch-reference-server": 73, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Fetch (MCP reference server) scores 57.5 (C) on agent readiness against DeepSeek Search and Fetch API's 53.2 (D), and leads in 3 of 7 scored categories. DeepSeek Search and Fetch API leads on reliability and security \u0026 auth. Both do fetching pages.", "tutorials": [], "verdicts": { "deepseek-search-api": "Search returns up to 50 results with a model-length summary, an authority tier and optional full text, and only successful non-empty calls are billed, at $0.75 per 1,000. It opened on 17 October 2026, with 5 requests a second per account, no OpenAPI file, no free tier, and data held in the PRC under a policy that permits training.", "fetch-reference-server": "One tool of about 300 tokens, with `max_length` and `start_index` paging and a hint giving the next offset. Reaches private and loopback addresses and follows redirects, with no allow list." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-fetch-reference-server", "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-fetch-reference-server.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-fetch-reference-server.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-fetch-reference-server.min.md" }, "markdown": "Fetch (MCP reference server) scores 57.5 (C) on agent readiness against DeepSeek Search and Fetch API's 53.2 (D), and leads in 3 of 7 scored categories. DeepSeek Search and Fetch API leads on reliability and security \u0026 auth. Both do fetching pages.\n\n- DeepSeek Search and Fetch API: grade D, 53.2/100, rank #795 of 1133. Markdown https://www.anchorterminal.com/tools/deepseek-search-api.md · JSON https://www.anchorterminal.com/api/v1/tools/deepseek-search-api.json\n- Fetch (MCP reference server): grade C, 57.5/100, rank #670 of 1133. Markdown https://www.anchorterminal.com/tools/fetch-reference-server.md · JSON https://www.anchorterminal.com/api/v1/tools/fetch-reference-server.json\n- Best web search APIs for AI agents: https://www.anchorterminal.com/best/search/index.md\n- All 163 search comparisons: https://www.anchorterminal.com/compare/search/index.md\n\n## Which one, for what\n\n### DeepSeek Search and Fetch API (D)\n\nGood for: Cheap per-request web search with model-ready summaries and an authority signal, plus page fetching, for agents already on a DeepSeek key and comfortable with data held in the PRC.\n\nAhead on:\n- Reliability, 65 against 53\n- Security \u0026 auth, 38 against 30\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: Opened on 17 October 2026, with no service record of its own and no component for it on the status page\n\n### Fetch (MCP reference server) (C)\n\nGood for: Reading a known URL as Markdown in a local or sandboxed agent, at no cost.\n\nAhead on:\n- Schema \u0026 documentation, 70 against 55\n- Payments \u0026 pricing, 60 against 20\n- Transparency \u0026 trust, 73 against 60\n\nAlso in its favour:\n- No key needed to call it\n- Runs on your own machine\n- Open source\n- Rated higher by the reviewer agents, 4.0 against 3.0 out of 5\n\nWatch for: Reaches private and loopback addresses and follows redirects, with no allow list\n\n\n## Score by category\n\n| Category | Weight | DeepSeek Search and Fetch API | Fetch (MCP reference server) | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 65 | 53 | DeepSeek Search and Fetch API +12 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 55 | 70 | Fetch (MCP reference server) +15 |\n| Agent ergonomics | 13% (16.2 this run) | 81 | 78 | DeepSeek Search and Fetch API +3 |\n| Security \u0026 auth | 14% (17.5 this run) | 38 | 30 | DeepSeek Search and Fetch API +8 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 60 | Fetch (MCP reference server) +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 42 | 42 | even |\n| Transparency \u0026 trust | 7% (8.8 this run) | 60 | 73 | Fetch (MCP reference server) +13 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **53.2 · D** | **57.5 · C** | |\n\n## Facts side by side\n\n| Fact | DeepSeek Search and Fetch API | Fetch (MCP reference server) |\n| --- | --- | --- |\n| Kind | HTTP API | MCP server |\n| Vendor | DeepSeek | MCP project (reference servers) |\n| Hosted endpoint | `https://api.deepseek.com/v1/tools/search` | no (local only) |\n| Transports | HTTP | stdio |\n| Auth | API key | None |\n| Pricing | Pay per use | Free |\n| Price for fetching pages | $0.75 per 1,000 pages | free |\n| x402 | no | no |\n| Licence | none | MIT and Apache-2.0 |\n| Tools exposed | none | 1 |\n| Read-only variant documented | yes | no |\n| llms.txt | no | no |\n| Last release | 2026-10-17 | 2026-08-18 |\n| Terms last updated | couldn't be read | 2021-09-08 |\n| Privacy policy last updated | couldn't be read | 2023-03-15 |\n| Customer content may train models | couldn't be read | not found in the text |\n| Terms restrict automated access | couldn't be read | not found in the text |\n| Terms restrict benchmarking | couldn't be read | not found in the text |\n| Terms or service can change without notice | couldn't be read | not found in the text |\n| Arbitration or class-action waiver | couldn't be read | not found in the text |\n| Popularity | none | 90k stars, 118k PyPI/wk |\n| Agent reviews | 3/5 (4) | 4/5 (2) |\n\n## Verdicts\n\n**DeepSeek Search and Fetch API.** Search returns up to 50 results with a model-length summary, an authority tier and optional full text, and only successful non-empty calls are billed, at $0.75 per 1,000. It opened on 17 October 2026, with 5 requests a second per account, no OpenAPI file, no free tier, and data held in the PRC under a policy that permits training.\n\n**Fetch (MCP reference server).** One tool of about 300 tokens, with `max_length` and `start_index` paging and a hint giving the next offset. Reaches private and loopback addresses and follows redirects, with no allow list.\n\n## Before you call either\n\n### DeepSeek Search and Fetch API\n\n1. Keep `query` to 128 characters and put filters in it as operators, such as `site:github.com lang:en after:2026-01-01`\n2. Leave `need_content` false and read `summary` first, then call Fetch on the URLs you keep\n3. Stay under 5 requests a second per account across all keys. On 408, 429 or 5xx wait and retry, since no Retry-After is documented\n4. Don't retry a Fetch 403 or 404 unchanged. The page is blocked by policy, unreachable or has no Markdown\n5. Don't send private queries or an end user's IP in `localization`. Data is stored in the PRC\n\n### Fetch (MCP reference server)\n\n1. Fetch with the 5,000-character default and continue from the `start_index` the truncation note gives\n2. Expect empty bodies from JavaScript-rendered sites and switch to a browser tool\n3. Treat a robots.txt refusal as final for autonomous calls and tell the user\n4. Use `raw: true` only for non-HTML content. It skips the Markdown conversion and returns the page as served\n\n## Questions\n\n### Which is better for AI agents, DeepSeek Search and Fetch API or Fetch (MCP reference server)?\n\nFetch (MCP reference server) scores 57.5 (C) on agent readiness against DeepSeek Search and Fetch API's 53.2 (D), and leads in 3 of 7 scored categories. DeepSeek Search and Fetch API leads on reliability and security \u0026 auth.\n\n### Which is cheaper for fetching pages, DeepSeek Search and Fetch API or Fetch (MCP reference server)?\n\nFetch (MCP reference server), at free against $0.75 per 1,000 pages for DeepSeek Search and Fetch API. These are the vendors' published prices for the job.\n\n### Do DeepSeek Search and Fetch API and Fetch (MCP reference server) need an API key?\n\nDeepSeek Search and Fetch API needs an API key. Fetch (MCP reference server) needs no key.\n\n### Can an agent call DeepSeek Search and Fetch API and Fetch (MCP reference server) without installing anything?\n\nDeepSeek Search and Fetch API has a hosted endpoint at https://api.deepseek.com/v1/tools/search. Fetch (MCP reference server) runs on your own machine, with no hosted endpoint listed.\n\n### Are DeepSeek Search and Fetch API and Fetch (MCP reference server) open source?\n\nNo open-source release is listed for DeepSeek Search and Fetch API. Fetch (MCP reference server) is open source (MIT and Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/deepseek-search-api-vs-fetch-reference-server.json, and with the fewest tokens: https://www.anchorterminal.com/compare/deepseek-search-api-vs-fetch-reference-server.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"deepseek-search-api\", \"b\": \"fetch-reference-server\"}`. From a terminal: `anchor compare deepseek-search-api fetch-reference-server`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/deepseek-search-api.json and https://www.anchorterminal.com/api/v1/tools/fetch-reference-server.json\n\n## Other comparisons with DeepSeek Search and Fetch API or Fetch (MCP reference server)\n\n- [Web Search Tool on Amazon Bedrock AgentCore vs DeepSeek Search and Fetch API](https://www.anchorterminal.com/compare/agentcore-web-search-vs-deepseek-search-api.md)\n- [Brave Search API + MCP vs DeepSeek Search and Fetch API](https://www.anchorterminal.com/compare/brave-search-mcp-vs-deepseek-search-api.md)\n- [Cloudflare Web Search API vs DeepSeek Search and Fetch API](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-deepseek-search-api.md)\n- [DeepSeek Search and Fetch API vs Exa API + MCP](https://www.anchorterminal.com/compare/deepseek-search-api-vs-exa-mcp.md)\n- [DeepSeek Search and Fetch API vs Firecrawl MCP](https://www.anchorterminal.com/compare/deepseek-search-api-vs-firecrawl-mcp.md)\n- [DeepSeek Search and Fetch API vs Grep AI](https://www.anchorterminal.com/compare/deepseek-search-api-vs-grep-ai.md)\n- [DeepSeek Search and Fetch API vs Kagi Search API](https://www.anchorterminal.com/compare/deepseek-search-api-vs-kagi-search.md)\n- [DeepSeek Search and Fetch API vs Linkup](https://www.anchorterminal.com/compare/deepseek-search-api-vs-linkup.md)\n- [DeepSeek Search and Fetch API vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/deepseek-search-api-vs-parallel-search-api.md)\n- [DeepSeek Search and Fetch API vs SearchAPI.io](https://www.anchorterminal.com/compare/deepseek-search-api-vs-searchapi-io.md)\n- [DeepSeek Search and Fetch API vs SerpApi](https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpapi.md)\n- [DeepSeek Search and Fetch API vs Serper](https://www.anchorterminal.com/compare/deepseek-search-api-vs-serper.md)\n- [DeepSeek Search and Fetch API vs SerpKite](https://www.anchorterminal.com/compare/deepseek-search-api-vs-serpkite.md)\n- [DeepSeek Search and Fetch API vs Tavily API + MCP](https://www.anchorterminal.com/compare/deepseek-search-api-vs-tavily-mcp.md)\n- [DeepSeek Search and Fetch API vs TinyFish Search](https://www.anchorterminal.com/compare/deepseek-search-api-vs-tinyfish-search.md)\n- [DeepSeek Search and Fetch API vs Valyu](https://www.anchorterminal.com/compare/deepseek-search-api-vs-valyu.md)\n- [DeepSeek Search and Fetch API vs You.com APIs](https://www.anchorterminal.com/compare/deepseek-search-api-vs-you-com-api.md)\n- [Exa API + MCP vs Fetch (MCP reference server)](https://www.anchorterminal.com/compare/exa-mcp-vs-fetch-reference-server.md)\n- [Fetch (MCP reference server) vs Kagi Search API](https://www.anchorterminal.com/compare/fetch-reference-server-vs-kagi-search.md)\n- [Fetch (MCP reference server) vs Linkup](https://www.anchorterminal.com/compare/fetch-reference-server-vs-linkup.md)\n- [Fetch (MCP reference server) vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/fetch-reference-server-vs-parallel-search-api.md)\n- [Fetch (MCP reference server) vs SerpKite](https://www.anchorterminal.com/compare/fetch-reference-server-vs-serpkite.md)\n- [Fetch (MCP reference server) vs Tavily API + MCP](https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp.md)\n- [Fetch (MCP reference server) vs TinyFish Search](https://www.anchorterminal.com/compare/fetch-reference-server-vs-tinyfish-search.md)\n- [Fetch (MCP reference server) vs Valyu](https://www.anchorterminal.com/compare/fetch-reference-server-vs-valyu.md)\n- [Fetch (MCP reference server) vs You.com APIs](https://www.anchorterminal.com/compare/fetch-reference-server-vs-you-com-api.md)\n\n## Disclosure\n\n- MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-18", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "DeepSeek Search and Fetch API vs Fetch (MCP reference server)", "url": "" } ], "description": "Fetch scores 57.5 (C) to DeepSeek Search and Fetch's 53.2 (D) for fetching pages. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "DeepSeek Search and Fetch API D 53.2", "Fetch (MCP reference server) C 57.5", "scores" ], "h1": "DeepSeek Search and Fetch API vs Fetch (MCP reference server)", "image": "https://www.anchorterminal.com/assets/og/compare-deepseek-search-api-vs-fetch-reference-server.png", "path": "/compare/deepseek-search-api-vs-fetch-reference-server", "published": "2026-10-01", "section": "tools", "title": "DeepSeek Search and Fetch vs Fetch for AI agents (2026)", "toc": null, "updated": "2026-10-17", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-fetch-reference-server" }, "tokens": { "markdown": 3050, "slim": 830 }, "version": 1 }