What it does
Claude alone cannot read the live web past its training cutoff. The usual workaround is to spin up a scraper or headless browser, post-process the result, and paste it back into context β each siteβs JavaScript rendering, markup quirks, and auth flow making that a per-target project.
Firecrawl MCP delegates the whole step. Claude calls the tools directly, and Firecrawl returns clean, LLM-ready markdown or structured JSON ready to drop into context.
Key features β 12+ tools
-
Scraping β
firecrawl_scrape/firecrawl_batch_scrape/firecrawl_check_batch_statusExtract a single URL into JSON, markdown, or branding format, or process many known URLs in parallel. Batch runs asynchronously; poll progress with
firecrawl_check_batch_status. -
Site discovery β
firecrawl_map/firecrawl_crawl/firecrawl_check_crawl_statusUse
firecrawl_mapto discover indexed URLs on a site, andfirecrawl_crawlto walk multiple pages with depth and page limits. Crawl runs asynchronously and is polled. -
Web search β
firecrawl_searchReturns search results with optional content extraction for each hit.
-
Structured extraction β
firecrawl_extractApplies an LLM against the target page to produce JSON conforming to a schema you provide β useful when text-only output isnβt enough.
-
Autonomous research agent β
firecrawl_agent/firecrawl_agent_statusHand the agent a topic and it runs multi-source research asynchronously. Poll progress with
firecrawl_agent_status. -
Interactive page automation β
firecrawl_interactClick, type, and navigate to reach content that static scraping cannot.
-
Cloud browser sessions β
firecrawl_browser_*(deprecated)firecrawl_browser_create,execute,list,deleteexist but are marked deprecated. New integrations should prefer the other tools.
Installation
Claude Code (recommended)
claude mcp add firecrawl \
--env FIRECRAWL_API_KEY="fc-YOUR_API_KEY" \
-- npx -y firecrawl-mcp
Direct npx
env FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp
Claude Desktop Β· Cursor Β· Windsurf Β· VS Code β add to the clientβs mcpServers JSON config:
{
"mcpServers": {
"mcp-server-firecrawl": {
"command": "npx",
"args": ["-y", "firecrawl-mcp"],
"env": { "FIRECRAWL_API_KEY": "YOUR_API_KEY_HERE" }
}
}
}
Config locations differ per client β Claude Desktop uses claude_desktop_config.json, Cursor v0.48.6+ via Settings β Features β MCP Servers, Windsurf at ./codeium/windsurf/model_config.json.
HTTP Streamable mode β for shared or remote environments.
env HTTP_STREAMABLE_SERVER=true FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp
# Accessible at http://localhost:3000/mcp
Self-hosted Firecrawl β set FIRECRAWL_API_URL to your own Firecrawl instance and the cloud API key requirement is bypassed (unless your instance itself requires authentication).
Environment variables
| Variable | Required | Default | Purpose |
|---|---|---|---|
FIRECRAWL_API_KEY | β (for cloud) | β | Firecrawl cloud API key. Generate at https://www.firecrawl.dev/app/api-keys |
FIRECRAWL_API_URL | cloud default | Self-hosted instance endpoint β bypasses cloud API when set | |
FIRECRAWL_RETRY_MAX_ATTEMPTS | 3 | Retry attempts | |
FIRECRAWL_RETRY_INITIAL_DELAY | 1000ms | Initial retry delay | |
FIRECRAWL_RETRY_MAX_DELAY | 10000ms | Max retry delay | |
FIRECRAWL_RETRY_BACKOFF_FACTOR | 2 | Exponential backoff factor | |
FIRECRAWL_CREDIT_WARNING_THRESHOLD | 1000 | Warn when remaining credits drop below | |
FIRECRAWL_CREDIT_CRITICAL_THRESHOLD | 100 | Critical warning threshold |
Notes
- Officially operated by Firecrawl β maintained in the
github.com/firecrawlorg, distinct from community wrappers. - Firecrawl is a separate service β a Y Combinator-backed company at firecrawl.dev. Free plan: 1,000 credits/month. Search results and page scrapes cost 1 credit each, interactions 5 credits each. Failed requests typically arenβt charged.
- Self-host option β for full data and cost control, set
FIRECRAWL_API_URLto your own Firecrawl instance. - Built-in retry + credit monitoring β exponential-backoff retries and remaining-credit warnings are tuned via the env vars above.
- Built on the open-source Firecrawl engine β the API this MCP calls is backed by
firecrawl/firecrawl, published under AGPL-3.0 (β 118k). Point it at a self-hosted instance withFIRECRAWL_API_URLto use the same toolset without the cloud. - A separate plugin exists at claude.com/plugins/firecrawl β same Firecrawl service, different distribution channel: Claude Code-specific slash commands (
/firecrawl:scrape, etc.). This MCP server uses standard MCP tool calls (firecrawl_scrape, etc.), which work across Cursor, Windsurf, VS Code, and any other MCP client. - MIT licensed β free for commercial and personal use.