{
  "name": "io.github.modelcontextprotocol/servers",
  "description": "The Fetch MCP lets AI models retrieve any web page URL and receive a clean, markdown-formatted version of the content. No API key required. Fast, simple, and useful for reading documentation, articles, and pages inside an AI context.",
  "status": "active",
  "version": "latest",
  "_meta": {
    "com.top-mcps/lastVerified": "2026-05-31",
    "com.top-mcps/score": {
      "value": 93,
      "rubricVersion": "2026-04",
      "lastComputed": "2026-06-02T13:16:41.473Z",
      "methodology": "https://top-mcps.com/about/methodology"
    },
    "com.top-mcps/stats": {
      "fetchedAt": "2026-06-02T11:55:51.467Z",
      "githubStars": 84102,
      "lastCommitAt": "2026-04-17T22:59:54Z"
    }
  },
  "repository": {
    "url": "https://github.com/modelcontextprotocol/servers/tree/main/src/fetch",
    "source": "github"
  },
  "author": {
    "name": "Anthropic (modelcontextprotocol)"
  },
  "packages": [
    {
      "registryType": "pypi",
      "registryBaseUrl": "https://pypi.org",
      "identifier": "mcp-server-fetch",
      "version": "latest",
      "transport": {
        "type": "stdio"
      }
    }
  ],
  "capabilities": {
    "tools": [
      {
        "name": "fetch",
        "description": "Fetch a URL and return its content converted to markdown.",
        "sideEffect": "network",
        "args": [
          {
            "name": "url",
            "type": "string",
            "required": true
          },
          {
            "name": "max_length",
            "type": "number",
            "required": false
          },
          {
            "name": "start_index",
            "type": "number",
            "required": false
          },
          {
            "name": "raw",
            "type": "boolean",
            "required": false
          }
        ]
      }
    ],
    "security": {
      "scope": "network",
      "sandbox": "Makes outbound HTTP(S) requests to the URL given in the tool call. No authentication or proxy support by default.",
      "gotchas": [
        "No URL allow-list by default — the agent can fetch any public URL. Combine with a client-side approval step for sensitive workflows.",
        "Large pages are truncated; do not rely on it for >~1MB documents."
      ]
    }
  },
  "_links": {
    "html": "https://top-mcps.com/mcp/fetch",
    "markdown": "https://top-mcps.com/mcp/fetch.md",
    "methodology": "https://top-mcps.com/about/methodology"
  }
}