web-fetcher

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.vojtisprime11/web-fetcher",
  "description": "Turns any web page into clean Markdown, page metadata and classified links for LLMs.",
  "repository": {
    "url": "https://github.com/vojtisprime11/mcp-server-web-fetcher",
    "source": "github"
  },
  "version": "0.1.0",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "mcp-server-web-fetcher",
      "version": "0.1.0",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Request timeout in milliseconds (1000-120000). Defaults to 15000.",
          "format": "number",
          "name": "WEB_FETCHER_TIMEOUT_MS"
        },
        {
          "description": "Maximum bytes downloaded per response. Defaults to 5000000.",
          "format": "number",
          "name": "WEB_FETCHER_MAX_BYTES"
        },
        {
          "description": "User-Agent header sent with every request.",
          "format": "string",
          "name": "WEB_FETCHER_USER_AGENT"
        },
        {
          "description": "Set to true to allow fetching loopback and private network addresses. Disables the SSRF guard.",
          "format": "boolean",
          "name": "WEB_FETCHER_ALLOW_PRIVATE_HOSTS"
        },
        {
          "description": "Set to true to enforce robots.txt before fetching.",
          "format": "boolean",
          "name": "WEB_FETCHER_RESPECT_ROBOTS"
        }
      ]
    }
  ]
}