Firecrawl MCP server for AI agents

Scrape pages into clean markdown, crawl and map whole websites, and search the web with page content.

Auth
Access token
Tools
6
Triggers
0
Category
Search, AI
Connect Firecrawl www.firecrawl.dev

Tools and triggers

  • Scrape a page

    FIRECRAWL_SCRAPE

    Loads one URL (running its JavaScript) and returns clean markdown, HTML or links.read-only

  • Start a crawl

    FIRECRAWL_START_CRAWL

    Starts crawling a website in the background and returns a job id. Poll with Get crawl status.

  • Get crawl status

    FIRECRAWL_GET_CRAWL_STATUS

    Returns the status of a crawl job and the pages scraped so far (status, total, completed, data).read-only

  • Cancel a crawl

    FIRECRAWL_CANCEL_CRAWL

    Stops a running crawl job. Pages already scraped stay available.destructive

  • Map a website

    FIRECRAWL_MAP

    Quickly lists the URLs of a website, optionally ranked against a search term.read-only

  • Search the web

    FIRECRAWL_SEARCH

    Searches the web and optionally scrapes each result page into markdown.read-only

Connect via MCP

Create an MCP server for Firecrawl in the dashboard, then add its URL to your client. This is the Claude Code command; the client guide has the others.

terminal
claude mcp add --transport http firecrawl \
  "https://www.prompt-tm.com/mcp/<server id>?user_id=<your user>" \
  --header "x-api-key: ptm_…"

Connect via REST

Run a tool with one request. The response is { data, error, successful, log_id } for every tool.

terminal
curl -X POST https://www.prompt-tm.com/api/v3/tools/execute/FIRECRAWL_SCRAPE \
  -H "x-api-key: $PROMPT_TM_KEY" -H "content-type: application/json" \
  -d '{ "user_id": "alice", "arguments": {} }'

Firecrawl questions

Other toolkits