MCP server

Firecrawl

io.github.pipeworx-io/firecrawl

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Firecrawl MCP — wraps the Firecrawl API (firecrawl.dev) for web scraping / crawling / search…

Website Source

At a glance

Type

MCP server

Publisher

pipeworx.io (verified by the MCP Registry)

Status

Working at last check

Tools

45

Token cost

About 27,073 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http firecrawl https://gateway.pipeworx.io/firecrawl/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.firecrawl]
url = "https://gateway.pipeworx.io/firecrawl/mcp"

Gemini CLI

{"mcpServers":{"firecrawl":{"httpUrl":"https://gateway.pipeworx.io/firecrawl/mcp"}}}

Cursor

{"mcpServers":{"firecrawl":{"url":"https://gateway.pipeworx.io/firecrawl/mcp"}}}

VS Code

{"servers":{"firecrawl":{"type":"http","url":"https://gateway.pipeworx.io/firecrawl/mcp"}}}

Antigravity

agy mcp add firecrawl https://gateway.pipeworx.io/firecrawl/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"firecrawl","server_url":"https://gateway.pipeworx.io/firecrawl/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"firecrawl","server_url":"https://gateway.pipeworx.io/firecrawl/mcp"}

Tools

• map ~233 tokens
  Crawl 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[]}.
• scrape Browses the web · ~318 tokens
  Scrape 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). Supports output formats: markdown, html, rawHtml, links.
• search ~219 tokens
  Run 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, description}]}.

Browse

• GitHub tools
• Firecrawl tools
• Web scraping
• Web search
• Website monitoring
• Converting to Markdown

Related MCP servers

• Fuze Data Tools
  No-code web scraping & data-extraction Apify actors: scrape and enrich web data at scale.
• Hyperbrowser
  Hyperbrowser MCP — wraps the Hyperbrowser AI-agent browsing API
• Firecrawl MCP Server
  Firecrawl, the context API for AI agents: search, scrape, interact with the web, plus paper search.
• Hydrafetch
  Turn any URL into clean Markdown and structured data. Scrape, crawl, search and extract.
• oassis — web scraping, crawling and browser control for AI agents
  Web Tools and Web Tasks for AI agents. 100-credit MCP trial; API-key credits or x402.
• Decodo
  Decodo MCP — wraps the Decodo Web Scraping API (decodo.com, formerly Smartproxy). Rotating…
• Web Search & Data API
  Web search, scraping, Google Trends and data lookups. Paid per call in USDC on Base via x402.
• Tollmint
  Per-call data for agents: graded behavioural science, dark-pattern detection, web fetch, geocode.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.pipeworx-io/firecrawl.svg)](https://aptlynx.net/servers/io.github.pipeworx-io/firecrawl)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents