#88th of 12 in MCP servers
firecrawl-mcp-server
MCP server giving agents Firecrawl web search, scraping, crawling and browser actions
- Stars
- 7.8k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- JavaScript
6,034 on 21 Apr 20267,800 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Firecrawl is hiring: 24 open roles
Overview
Wraps the Firecrawl API as an MCP server so clients like Cursor, Windsurf, VS Code and Claude Desktop can search, scrape, crawl, map and interact with web pages and get back Markdown or structured data. It runs over stdio via npx or Docker, as local Streamable HTTP on port 3000, or as a hosted endpoint with a keyless free tier limited to scrape, search and parse. It can target the cloud API or a self-hosted Firecrawl through FIRECRAWL_API_URL.
Who it is for: Developers giving MCP clients live web search and scraping
Strengths
- Covers scrape, crawl, map, search, browser interact, monitoring and agent jobs in one server
- Hosted keyless endpoint offers scrape, search and parse without signup
- Runs via npx, Docker image or local Streamable HTTP; supports self-hosted Firecrawl
- Local HTTP mode checks Host and Origin headers to block DNS rebinding
Weaknesses
- Cloud use needs a Firecrawl API key and consumes paid credits
- Full profile registers 31 tools, which can strain clients with tool-slot limits
- Keyless tier is rate-limited and excludes crawl, map and agent
- Interact calls run one turn to completion; no step-by-step client-side control
What it needs
- no GPU
- Docker
- Needs Firecrawl API (cloud or self-hosted), Node.js (npx)
- port 3000
Quick answers
Is firecrawl-mcp-server open source?
Yes. Its code is on GitHub under the MIT license.
Can you run firecrawl-mcp-server with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does firecrawl-mcp-server need a GPU?
No, it runs without one.
Also in MCP servers
See all 12| Rank | Project | Score |
|---|---|---|
| 1 | serversReference MCP servers for files, git, fetch, memory and time | 94 out of 100 |
| 2 | apify-mcp-serverOfficial MCP server exposing Apify Store Actors as tools for web scraping | 86 out of 100 |
| 3 | xiaohongshu-mcpMCP server that lets AI clients post, search and comment on Xiaohongshu | 85 out of 100 |
| #4 | ha-mcpMCP server that lets AI assistants configure and control Home Assistant | 80 out of 100 |
| #5 | mcp-atlassianMCP server exposing Jira and Confluence tools to AI assistants | 69 out of 100 |