MCP Server MCP

webfetch

By github 👁 1 views ▲ 0 votes

Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching

Homepage Verified source GitHub

Install

uvx webfetch-llm

Configuration Example

{
  "remotes": [],
  "packages": [
    {
      "registryType": "pypi",
      "registryBaseUrl": "https://pypi.org",
      "identifier": "webfetch-llm",
      "version": "0.1.3",
      "runtimeHint": "uvx",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Optional - adds Brave to the multi-engine fusion. DDG works with no keys at all.",
          "isSecret": true,
          "name": "BRAVE_API_KEY"
        },
        {
          "description": "Optional - adds Serper (Google results) to the multi-engine fusion.",
          "isSecret": true,
          "name": "SERPER_API_KEY"
        },
        {
          "description": "Optional - adds Tavily to the multi-engine fusion.",
          "isSecret": true,
          "name": "TAVILY_API_KEY"
        },
        {
          "description": "Optional - search strategy: multi (RRF fusion of available engines, default), fallback (priority failover), or a single engine name like ddg.",
          "name": "WEBFETCH_PROVIDER"
        }
      ]
    }
  ]
}

mcp model-context-protocol pypi