How to Connect Firecrawl to an AI Agent
Auth setup
1. Sign up at firecrawl.dev. 2. Get API key from dashboard. 3. Use as Bearer token in Authorization header.
Key facts
| Base URL | https://api.firecrawl.dev/v1/ |
| API version | v1 |
| Auth | API key as Bearer token. Get key at firecrawl.dev. |
| Request body | application/json |
| Pagination | Crawl is async — poll GET /crawl/{id} for status and results. |
| Rate limit | Free: 500 credits/month. Each scrape = 1 credit, crawl pages = 1 credit each. |
| Error format | JSON: {"success":false,"error":"..."} |
Key endpoints
| Method | Path | Description |
POST | /scrape | Scrape a single URL to markdown/structured data |
POST | /crawl | Crawl entire website |
POST | /map | Map site structure (sitemap discovery) |
Quickstart
POST /v1/scrape
Authorization: Bearer {api_key}
{"url":"https://example.com","formats":["markdown"]}
Agent pitfalls & tips
- Returns clean markdown — perfect for feeding into LLMs.
- Use formats=['markdown','html'] to get both versions.
- Crawl is asynchronous — returns job_id, poll for completion.
- Self-hostable via Docker for unlimited usage.
- Official MCP server available for agent web scraping workflows.
Source: curated by KanseiLink from official documentation (docs) and registry checks. Last reviewed: 2026-04-07. Specs change — verify against the official docs before production use.
Frequently Asked Questions
What is Firecrawl's AEO score?
▼
Firecrawl has an AEO score of 0.90 and is rated AA (Strong agent support with minor gaps). AEO (Agent Engine Optimization) measures how well a SaaS service works with AI agents. Scores range from 0.00 to 1.00, with grades from AAA (best) to D (not agent-ready).
Is Firecrawl AI-agent-ready?
▼
Firecrawl is currently ✓ verified for AI agent use. It offers an official MCP (Model Context Protocol) server, which means AI agents can connect directly. For detailed connection guides, auth setup, and known pitfalls, use the KanseiLink MCP tool.
How does Firecrawl compare to other Data Integration services?
▼
In the Data Integration category, Firecrawl is rated AA. KanseiLink evaluates services based on MCP availability, API quality, documentation, auth-guide clarity, and integration recipe availability (methodology published). Visit the full rankings at kansei-link.com to see how Firecrawl compares.
How can I integrate Firecrawl with an AI agent?
▼
The fastest way to integrate Firecrawl with an AI agent is through KanseiLink MCP. Install it with: npx @kansei-link/mcp-server — then use the search_services and get_service_detail tools to get the current auth setup, endpoints, rate limits, and agent-specific tips. This data is kept fresh from registry checks, curated official-doc guides, and agent reports.
How do I authenticate with Firecrawl?
▼
API key as Bearer token. Get key at firecrawl.dev. Setup: 1. Sign up at firecrawl.dev. 2. Get API key from dashboard. 3. Use as Bearer token in Authorization header.
What are Firecrawl's API rate limits?
▼
Free: 500 credits/month. Each scrape = 1 credit, crawl pages = 1 credit each.