Home › Search & Research › webfetch

webfetch

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

Python

★ 56 stars Last pushed 2026-07-23 License: MIT

View repository →

Connect

Review any command before running it. Package names and URLs come from the server's own registry entry.

Package (pypi 0.1.3)

uvx webfetch-llm

Or add to your MCP client config:

{
  "mcpServers": {
    "webfetch": {
      "command": "uvx",
      "args": [
        "webfetch-llm"
      ],
      "env": {
        "BRAVE_API_KEY": "<YOUR_VALUE>",
        "SERPER_API_KEY": "<YOUR_VALUE>",
        "TAVILY_API_KEY": "<YOUR_VALUE>",
        "WEBFETCH_PROVIDER": "<YOUR_VALUE>"
      }
    }
  }
}

BRAVE_API_KEY secret — Optional - adds Brave to the multi-engine fusion. DDG works with no keys at all.
SERPER_API_KEY secret — Optional - adds Serper (Google results) to the multi-engine fusion.
TAVILY_API_KEY secret — Optional - adds Tavily to the multi-engine fusion.
WEBFETCH_PROVIDER — Optional - search strategy: multi (RRF fusion of available engines, default), fallback (priority failover), or a single engine name like ddg.