Firecrawl
liveDeveloperAI/MLFirecrawl API (firecrawl.dev): scrape URLs to clean markdown, map all links on a website, and run web searches with optional page content.
Tools
scrapeScrape a single URL using Firecrawl's JS-rendering engine and return clean markdown (up to 100,000 chars), page title, and description. Strips navigation/boilerplate by default (only_main_content=true
No parameters required.
Try it
mapCrawl a website and return all discovered URLs (up to 5,000). Optionally filter by a search term to rank discovered links by relevance. Returns {url, count, links[]}.
No parameters required.
Try it
searchRun a web search via Firecrawl and return ranked results with URL, title, and description snippet. Takes a query string and optional limit (default 5, max 20). Returns {query, results[{url, title, des
No parameters required.
Try it
Test with curl
The gateway speaks JSON-RPC 2.0 over HTTP POST. You can test any pack directly from the terminal.
curl -X POST https://gateway.pipeworx.io/firecrawl/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'curl -X POST https://gateway.pipeworx.io/firecrawl/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"scrape","arguments":{}}}'Use with the SDK
Install @pipeworx/sdk to call tools from any TypeScript/Node project.
import { Pipeworx } from '@pipeworx/sdk';
const px = new Pipeworx();
const result = await px.call("scrape", {});// Or ask in plain English:
const answer = await px.ask("firecrawl api (firecrawl");