Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "contextfetch": {
      "type": "http",
      "url": "https://api.contextfetch.dev/mcp",
      "headers": {
        "x-api-key": "${X_API_KEY}"
      }
    }
  }
}

claude mcp add --transport http contextfetch https://api.contextfetch.dev/mcp --header "x-api-key: ${X_API_KEY}"

[mcp_servers.contextfetch]
url = "https://api.contextfetch.dev/mcp"
env_http_headers = { "x-api-key" = "X_API_KEY" }

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "contextfetch": {
      "type": "remote",
      "url": "https://api.contextfetch.dev/mcp",
      "enabled": true,
      "headers": {
        "x-api-key": "{env:X_API_KEY}"
      }
    }
  }
}

{
  "mcpServers": {
    "contextfetch": {
      "type": "http",
      "url": "https://api.contextfetch.dev/mcp",
      "headers": {
        "x-api-key": "${X_API_KEY}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=contextfetch&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLmNvbnRleHRmZXRjaC5kZXYvbWNwIiwiaGVhZGVycyI6eyJ4LWFwaS1rZXkiOiIke1hfQVBJX0tFWX0ifX0%3D"
}

{
  "servers": {
    "contextfetch": {
      "type": "http",
      "url": "https://api.contextfetch.dev/mcp",
      "headers": {
        "x-api-key": "${X_API_KEY}"
      }
    }
  }
}

{
  "mcpServers": {
    "contextfetch": {
      "httpUrl": "https://api.contextfetch.dev/mcp",
      "headers": {
        "x-api-key": "${X_API_KEY}"
      }
    }
  }
}

extensions:
  "contextfetch":
    enabled: true
    name: "contextfetch"
    type: streamable_http
    uri: "https://api.contextfetch.dev/mcp"
    headers:
      "x-api-key": "${X_API_KEY}"
    timeout: 300

Placeholders to fill from your own secret store: ${X_API_KEY}. The registry never accepts secret values.

Quality 81 / 100new

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene86 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations13 of 13 tools declare readOnlyHint or destructiveHint
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: contextfetch_search (destructiveHint, idempotentHint); contextfetch_find_similar (destructiveHint, idempotentHint); contextfetch_research (destructiveHint, idempotentHint); …
pass
tools.token_costabout 2,222 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stabilityn/a · weight 15

n/a
stability.changes, stability.rug_pulltool history recorded for 0 of the 7 days needed

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvabledependencies not resolved yet

13 tools, about 2,222 tokens to load them all · tool set 989e3c8d56c7 · checked 2026-10-20 10:03 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 96 / 100

provenance85

liveness100

freshness100

hygiene100

+repository +dns-namespace +website +reachable +uptime-100% +updated-1d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Dependencies

@contextfetch/[email protected] npmnot resolved yet; dependencies are read once a day

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://api.contextfetch.dev/mcp` streamable-http	none	yes	100%	516 ms	2025-06-18	2026-10-20

package	registry	version	runtime	secrets
`@contextfetch/mcp`	npm	1.0.1	npx	`CONTEXTFETCH_API_KEY`

Tools (13)

`contextfetch_answer`read-only	Answer a question with passages quoted verbatim from the web, never generated: searches, scores every passage of the top pages with a cross-encoder and returns the best ones with [n] citations to their sources. Use it for quick factual lookups; the quotes may not fully answer an open-ended question. Costs 1 credit.
`contextfetch_auto_reload`	Turn auto-reload on or off, or change it: when credits drop below `threshold`, the saved card buys `pack` again, up to `monthly_max_usd` per month. Needs an API key and a card saved at checkout. The monthly cap cannot be raised above $500 here.
`contextfetch_balance`read-only	Show the API key's remaining credits, daily burn rate (7-day average) and auto-reload settings, including the last auto-reload error if a payment failed. Needs an API key (Authorization: Bearer); free.
`contextfetch_crawl`read-only	Crawl one website from a start URL and get its pages as Markdown: same-site links only, up to `max_depth` hops (<= 3) and `limit` pages (<= 50). Pass `query` to rank the pages by relevance and return only their relevant passages. Costs 1 credit per page returned.
`contextfetch_deep_research`read-only	Same as contextfetch_research (kept for existing clients): up to 3 sub-queries run server-side, sources deduped and ranked against the question, one Markdown evidence pack with numbered sources and query-pruned passages. Each sub-query is one search and costs 1 credit. You SHOULD pass your own `sub_queries` (up to 3 distinct angles on the question) for better coverage. If omitted, they are derived from `query`: the query itself, query + "documentation", and query + "benchmark" when it asks about speed, performance or comparisons, else query + "example".
`contextfetch_extract_url`read-only	Fetch a public web page (docs, articles, GitHub files, arXiv papers) as clean Markdown with tables preserved. Pass `query` to get only the passages relevant to it instead of the whole page.
`contextfetch_find_similar`read-only	Find pages similar to a given URL (alternatives, related docs, competing libraries), excluding the source domain. Returns titles, URLs and the most relevant passages as Markdown.
`contextfetch_get_free_key`	Get a free ContextFetch API key (no signup, no payment) with starter credits, for when the keyless daily limit runs out. One key per network, ever: keep the key it returns and use it as `Authorization: Bearer <key>`.
`contextfetch_map`read-only	List a website's URLs without fetching its pages: its sitemaps (from robots.txt, else /sitemap.xml) plus the start page's links, same site only, up to `limit` (<= 5,000). Use it to find the right pages before contextfetch_extract_url or contextfetch_crawl. Costs 1 credit.
`contextfetch_research`read-only	Research a question in one call, server-side: runs up to 5 web searches (sub-queries) concurrently, dedupes the pages by URL, ranks them all against the question with a cross-encoder and returns one Markdown evidence pack with numbered [n] sources and their query-pruned passages, quoted verbatim (no generated text). Costs 1 credit per sub-query. Pass your own `sub_queries` (distinct angles on the question) for better coverage; if omitted they are derived from `query`: the query, query + "documentation", and query + "benchmark" (speed or comparison questions) or + "example".
`contextfetch_search`read-only	Search the web and get LLM-ready Markdown. Each result has its title, URL and only the passages relevant to the query (cross-encoder pruned context), so it costs far fewer tokens than raw pages. Use for current events, documentation, APIs, research and fact checking.
`fetch`read-only	Fetch the full text of a search result by its id (a URL). Returns {id, title, text, url, metadata} as JSON.
`search`read-only	Search the web. Returns {results: [{id, title, url}]} as JSON; pass an id to `fetch` for the page text.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "dev.contextfetch/mcp",
  "icons": [
    {
      "src": "https://contextfetch.dev/logomark.svg",
      "sizes": [
        "any"
      ],
      "mimeType": "image/svg+xml"
    },
    {
      "src": "https://contextfetch.dev/apple-touch-icon.png",
      "sizes": [
        "180x180"
      ],
      "mimeType": "image/png"
    }
  ],
  "title": "ContextFetch",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://api.contextfetch.dev/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "x-api-key",
          "isSecret": true,
          "description": "ContextFetch API key. Leave unset for the free keyless tier (25 requests per day per IP)."
        }
      ]
    }
  ],
  "version": "1.0.1",
  "packages": [
    {
      "version": "1.0.1",
      "transport": {
        "type": "stdio"
      },
      "identifier": "@contextfetch/mcp",
      "runtimeHint": "npx",
      "registryType": "npm",
      "environmentVariables": [
        {
          "name": "CONTEXTFETCH_API_KEY",
          "format": "string",
          "isSecret": true,
          "description": "ContextFetch API key. Leave unset for the free keyless tier (25 requests per day per IP)."
        },
        {
          "name": "CONTEXTFETCH_API_BASE",
          "format": "string",
          "default": "https://api.contextfetch.dev",
          "description": "API base URL, only for a self-hosted engine."
        }
      ]
    }
  ],
  "repository": {
    "url": "https://github.com/lachy3433/contextfetch-mcp",
    "source": "github"
  },
  "websiteUrl": "https://contextfetch.dev",
  "description": "Web search and any page as LLM-ready Markdown for AI agents. Free keyless tier, no signup."
}