webfetch
01MCP server Claude CodeCodexCursor +2
MCP server "webfetch" as configured in firish/webfetch. Runs locally from the webfetch-llm@latest Python package.
55 1mo ago A
tokens not measured
original MIT
Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-tuned semantic caching with query-dependant TTL that no API offers.