Firecrawl logo
Firecrawl MCP

Firecrawl for your agent, through one MCP connection

Scrape pages to markdown, crawl sites and extract structured data through one MCP connection.

Give this to your agent
set up looot for Firecrawl jobs - https://looot.ai/mcp/firecrawl/skill.md

Connect in 30 seconds

Pick the client you use and add looot once. Firecrawl is then one of the tools behind it. Each client takes one step, then your agent does the rest.

  1. Claude Code
    01

    Claude Code

    Run this in your terminal, then sign in from the browser when it asks.

    Terminal command
    claude mcp add looot https://api.looot.ai/mcp --transport http
  2. Cursor
    02

    Cursor

    Create .cursor/mcp.json with this server, then sign in from the browser.

    mcp.json
    {"mcpServers":{"looot":{"url":"https://api.looot.ai/mcp"}}}
  3. ChatGPT
    03

    ChatGPT

    Where your plan lets you add a connector, add this URL and sign in.

    Connector URL
    https://api.looot.ai/mcp

Then tell your agent, in any client:

Agent setup line
set up https://looot.ai/skill.md

What to ask

Prompts for Firecrawl

Paste one into your agent after you connect looot.

Page to markdown
Use looot to scrape https://example.com/pricing with Firecrawl and return clean markdown.

Structured fields
Use looot to extract product name, price and plan limits from these five pages with Firecrawl as a table.

Crawl a site
Use looot to crawl the blog of https://example.com with Firecrawl and list every post title and date.

Jobs

What your agent can do with Firecrawl

Prices are the cheapest live endpoint for each job, read from the looot catalog.

Compare

Using Firecrawl directly versus through looot

The direct side comes from Firecrawl's own docs and pricing page.

Firecrawl directly versus through looot
Firecrawl directlyThrough looot
AccountA Firecrawl account and a Firecrawl API key.Yes. One looot sign-in. You do not set up a separate Firecrawl account.
PriceFirecrawl's own credit plans, billed by Firecrawl.Yes. Per call, shown before the run.
Finding the endpointFirecrawl's own MCP server or its API docs list its tools.Yes. Your agent searches the looot catalog for the task.
Other providersFirecrawl only. Each other provider needs its own account and key.Yes. The same connection reaches every provider in the catalog.

FAQ

Firecrawl MCP, answered

Firecrawl publishes its own MCP server. looot is not that server. looot is one MCP connection that reaches Firecrawl and every other provider in the catalog, billed per call. Use Firecrawl's server when Firecrawl is the only provider you need.

Add the looot MCP connection to Claude Code once, using the setup at https://looot.ai/skill.md. Then ask Claude Code to use looot for the job. Firecrawl is one of the providers behind looot; your agent calls its endpoints through the looot MCP connection.

Add the looot MCP connection in Cursor's MCP settings, then ask the agent to use looot. Firecrawl is one of the providers behind looot; your agent calls its endpoints through the looot MCP connection.

It works in any client that can add an MCP connection. Where your ChatGPT plan lets you add one, add looot and ask it to use looot. Firecrawl is one of the providers behind looot; your agent calls its endpoints through the looot MCP connection.

The jobs on this page: convert pages to markdown, extract structured data, crawl a whole site, map the urls of a site. The page marks any job whose endpoints are not in the live catalog.

You pay per call. The price of each endpoint is shown before you run it, so your agent can check it first and pick the cheapest one that fits.

You connect to looot, not to Firecrawl. looot makes the provider call for you and bills each call at the price shown before the run.

It searches the looot catalog for the task, reads the endpoint's parameters and price, and then calls it. You do not have to read Firecrawl's docs first.

Providers that often go with Firecrawl are Jina, Diffbot, Zyte API, Exa, Apify. All of them sit behind the same looot MCP connection.

For pages to markdown, Jina, Hyperbrowser and Steel run behind the same looot connection. For structured data, Diffbot, Zyte API and Jina. See /mcp/jina, /mcp/diffbot and /mcp/zyte-api, or ask your agent to compare prices in the looot catalog before it runs.

You pay per call, and one scrape call reads one page. The price of each Firecrawl endpoint is shown before the run, so your agent can compare it with Jina or Steel first.
For agents
provider
Firecrawl
role
Web scraping and crawling API
job
Convert pages to markdown: covered
job
Extract structured data: covered
job
Crawl a whole site: covered
job
Map the URLs of a site: covered
pair with
jina diffbot zyte-api exa apify
setup
https://looot.ai/mcp/firecrawl/skill.md
llms.txt
https://looot.ai/llms.txt
updated
2026-10-02

Give your agent Firecrawl and every other provider.

Start your workspace, top up, and paste one prompt into the agent you already use.