firecrawl.dev
Firecrawl is a web data platform for AI agents and applications that can search the web, scrape pages, crawl sites, map URLs, parse documents, and interact with pages through managed browser automation. It is offered as a hosted API service with accompanying CLI and MCP tooling.
Firecrawl exposes a documented HTTP API at https://api.firecrawl.dev/v2, a Node-based `firecrawl` CLI, and an MCP server documented for agent clients; authentication centers on Firecrawl API keys, with WorkOS ID-JAG supported as an agent-side registration flow to mint those keys.
- Firecrawl MCP Serverdiscovered
- Firecrawl API v2discovered
- Firecrawl CLIdiscovered
Sign up or sign in at Firecrawl. Then create or view your API key in the dashboard, or run the CLI login flow from Skills + CLI using firecrawl login --browser or firecrawl login --api-key .... The issued key has the fc-... format and is sent as Authorization: Bearer <token>.
conventions · 2/7 published
- integrations.json——
- llms.txt✓https://firecrawl.dev/llms.txt
- API catalog✗
/.well-known/api-catalog - OpenAPI document✗
/api/schema/, /openapi.json, /swagger.json, /api/openapi.json, or /v1/openapi.json - MCP server card✗
/.well-known/mcp/server-card.json - OAuth protected resource✓https://firecrawl.dev/.well-known/oauth-protected-resource
- Agent card✗
/.well-known/agent-card.json - Agent skills✗
/.well-known/agent-skills/index.json
Publish these signals → /publishing