webfetch

Overview

webfetch is a Model Context Protocol server that brings self-hosted web search to LLM agents through a search, fetch, and rank pipeline with semantic caching. By implementing MCP, it lets AI assistants call webfetch as native tools without manual data transfer between applications.

The server runs locally via the Python package webfetch-llm, installed through uvx and communicating over stdio. It requires an API key for authentication. The latest release is v0.1.3, published under the MIT license with source code available at firish/webfetch on GitHub, where the project has 55 stars.

webfetch is listed in the AI & Agents category on mcp.site and works with any MCP client including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain webfetch for firish, you can claim this listing to verify ownership and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "webfetch": {
      "command": "uvx",
      "args": [
        "webfetch-llm"
      ]
    }
  }
}