- CollectionBrowser & Web Execution
- Classificationagent-native
- MCPAvailable
- Agent SkillAvailable
- InterfacesAgent Skill · MCP · REST · SDK · API
What it does
Firecrawl is a web extraction API that converts websites into clean, LLM-ready markdown or structured JSON. Its /agent endpoint goes further: agents describe what data they need in natural language — no URLs required. Firecrawl autonomously searches, navigates, and extracts across multiple sources in parallel, returning structured output directly consumable by an LLM.
Agent-facing interfaces
- Catalog protocols: Agent Skill, MCP, REST, SDK, API
- MCP: ✅ Available
- Agent Skill: ✅ Official skill published at firecrawl/cli
- Onboarding type:
agent-skill
Protocol surface
| Interface | Detail |
|---|---|
| REST API | All endpoints (agent, scrape, crawl, extract, map) |
| Python SDK | pip install firecrawl-py; Pydantic schema support |
| Node.js SDK | npm install @mendable/firecrawl-js; Zod schema support |
| MCP Server | Model Context Protocol for direct LLM tool use |