Home › Browser Automation & Scraping › Firecrawl MCP Server
Firecrawl MCP Server
Firecrawl, the context API for AI agents: search, scrape, interact with the web, plus paper search.
Topics: Browser Automation
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Remote (streamable-http)
https://mcp.firecrawl.dev/v2/mcp Responded, but not as an MCP endpoint
Claude Code:
claude mcp add --transport http firecrawl-mcp-server https://mcp.firecrawl.dev/v2/mcp --header "Authorization: <YOUR_VALUE>"
Or add to your MCP client config:
{
"mcpServers": {
"firecrawl-mcp-server": {
"url": "https://mcp.firecrawl.dev/v2/mcp",
"headers": {
"Authorization": "<YOUR_VALUE>"
}
}
}
}
Authorizationsecret — Optional. Bearer <FIRECRAWL_API_KEY>. Get a key at https://firecrawl.dev/app/api-keys
Package (npm 3.39.0)
npx -y [email protected]
Or add to your MCP client config:
{
"mcpServers": {
"firecrawl-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"FIRECRAWL_API_KEY": "<YOUR_VALUE>"
}
}
}
}
FIRECRAWL_API_KEYsecret — Your API key for Firecrawl
Related servers
browser
Headless browser for AI and web automation with a built-in MCP server.
playwright-mcp
Playwright Tools for MCP
SeleniumBase MCP
Stealthy browser automation, testing, and web-scraping via CDP Mode.
browsermcp/mcp
Automate your local Chrome browser.
mcp-playwright
Browser automation and web scraping using Playwright.
auto-browser
Browser agent with human takeover via noVNC, reusable auth profiles, approval and audit controls, and isolated Docker sessions.
Listed in punkpeye/awesome-mcp-servers (MIT)
Listed in wong2/awesome-mcp-servers (MIT)
Data from the Official MCP Registry