Firecrawl
The official Firecrawl MCP server gives AI agents powerful web-data tools: scrape a single URL to clean markdown, map a site's URLs, crawl multiple pages, search the web, extract structured data with an LLM, run autonomous research agents, interact with dynamic pages, and monitor pages for changes.
Install Firecrawl
- Published by
- Official (vendor)
- Transport
- Remote (HTTP)
- Authentication
- API key
Claude Desktop, Claude Code and Cursor
Add this to the mcpServers object in your client's
config file, then restart the client.
{
"mcpServers": {
"firecrawl": {
"type": "http",
"url": "https://mcp.firecrawl.dev/v2/mcp",
"headers": {
"Authorization": "Bearer ${FIRECRAWL_API_KEY}"
}
}
}
}VS Code uses a different key — show that config
Identical entry, filed under servers rather than
mcpServers. Put it in
.vscode/mcp.json for one workspace.
{
"servers": {
"firecrawl": {
"type": "http",
"url": "https://mcp.firecrawl.dev/v2/mcp",
"headers": {
"Authorization": "Bearer ${FIRECRAWL_API_KEY}"
}
}
}
}Before it will answer
Firecrawl is explicit that the key goes in the Authorization header and never in the MCP URL — a key pasted into a URL ends up in client logs and config files that get shared. If your client supports a sign-in flow, point it at https://mcp.firecrawl.dev/v2/mcp-oauth instead and skip the key entirely.
Tools
firecrawl_agent
Run an autonomous web-research agent for multi-source gathering.
firecrawl_agent_status
Check status and retrieve results from an agent research job.
firecrawl_check_crawl_status
Check status and retrieve results of a running crawl job.
firecrawl_crawl
Extract content from many related pages with depth and limits.
firecrawl_extract
Extract structured information from web pages using an LLM.
firecrawl_interact
Click, type, navigate, and interact with dynamic web pages.
firecrawl_map
Discover all indexed URLs available on a target website.
firecrawl_monitor_create
Create a recurring page monitor with change detection.
firecrawl_monitor_run
Trigger an immediate change check on a page monitor.
firecrawl_parse
Parse local files or hosted uploads such as PDFs and Word docs.
firecrawl_research_search_github
Search GitHub repositories that are relevant to a given query.
firecrawl_research_search_papers
Search academic research papers across the web via Firecrawl.
firecrawl_scrape
Extract content from a single URL as markdown, JSON, or HTML.
firecrawl_search
Search the web and optionally extract content from results.