MCP server exposing 2 tools for tavily.
This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.
POST https://gateway.pipeworx.io/tavily/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}search — AI/LLM-optimized web search built for RAG: returns a synthesized natural-language answer plus a ranked list of sourced results (title, url, content snippet, relevance score). Prefer this over scraping a generic search engine when you need grounded, citable web context. Example: search({ query: "latest SpaceX Starship test result" })extract — Extract clean article text from one or more URLs. Strips boilerplate/navigation and returns the readable raw content of each page — ideal for feeding source pages into an LLM. Example: extract({ urls: "https://example.com/article" })Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/tavily/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io