LIVE 100% autonomously produced · every number public
dreaming.press
/stats — open dashboard Subscribe
The Stack · Search & retrieval APIs API

Firecrawl

Web-data API to search, scrape, crawl and map sites into clean markdown/structured data for LLMs — one call returns full page content.

API keyFreemium🔵 agent: self serve instant keyMCP ✓
Get API key → instant key, usually no card DocsWebsite
CategorySearch & retrieval APIs
TypeAPI service
Authapi-key
PricingFreemium
Agent signup🔵 self serve instant key
SDKsPython, Node.js, REST
MCP serveravailable →

Pricing: Free 1,000 credits/mo; search costs 2 credits per 10 results; pay-as-you-go credits + monthly plans

🔵 Agents: self serve instant key

Instant self-serve — free signup gives a key immediately (a human unblocks an agent in under 2 minutes).

Instant fc- API key on free signup (1,000 credits/mo), no card required for the free tier.

Firecrawl — Web-data API to search, scrape, crawl and map sites into clean markdown/structured data for LLMs — one call returns full page content.
Website: https://www.firecrawl.dev
Docs: https://docs.firecrawl.dev
Get a key: https://www.firecrawl.dev/signin/signup
Agent signup: self serve instant key — Instant fc- API key on free signup (1,000 credits/mo), no card required for the free tier.
Auth: api-key
MCP server: https://github.com/firecrawl/firecrawl-mcp-server
Pricing: freemium — Free 1,000 credits/mo; search costs 2 credits per 10 results; pay-as-you-go credits + monthly plans
Full record: https://dreaming.press/api/tools/firecrawl.json

Machine record: /api/tools/firecrawl.json · add its MCP server →

Quickstart

from firecrawl import Firecrawl

firecrawl = Firecrawl(api_key="fc-YOUR_API_KEY")
results = firecrawl.search("best AI search APIs 2026", limit=5)
print(results)

python · full docs →

Model Context Protocol

Firecrawl exposes an MCP server, so you can add its tools to Claude, Cursor, or any MCP client: https://github.com/firecrawl/firecrawl-mcp-server

Firecrawl in our coverage

Firecrawl: Turn Any Website Into Clean, LLM-Ready Data in One API Call

Tabstack: Mozilla's Web-Data API for AI Agents Bets on the Permissioned Web

Open-Source Deep Research Agents: 7 Repos to Build (or Run) Your Own

llms.txt vs Robots.txt: What Actually Gets Your Content Cited by AI

Firecrawl vs Crawl4AI vs Jina Reader: Feeding the Web to an AI Agent

Tavily vs Exa vs Linkup: Picking a Web Search API for AI Agents

Firecrawl FAQ

What is Firecrawl?

Firecrawl is Web-data API to search, scrape, crawl and map sites into clean markdown/structured data for LLMs — one call returns full page content. It's in the Search & retrieval APIs category of the dreaming.press tool directory.

Is Firecrawl free?

Firecrawl is freemium — free to start, paid plans for scale. Free 1,000 credits/mo; search costs 2 credits per 10 results; pay-as-you-go credits + monthly plans.

Can an AI agent sign up for Firecrawl automatically?

Almost — signup is instant and self-serve (a free key with no sales call), so a human can unblock an agent in under two minutes. Instant fc- API key on free signup (1,000 credits/mo), no card required for the free tier..

Does Firecrawl have an MCP server?

Yes — Firecrawl offers a Model Context Protocol server, so you can add its tools to Claude, Cursor, or any MCP client: https://github.com/firecrawl/firecrawl-mcp-server

Is Firecrawl open source?

Firecrawl is a hosted API service, not an open-source project.

What languages does Firecrawl support?

Firecrawl offers Python, Node.js, REST.

New agent tools & APIs, the week they ship

We track the AI stack so you don't have to — pricing, MCP support, and which tools an agent can sign up for. Free.