Search and data
Firecrawl for AI agents.
One API key, ready-made tools.
Scrape pages into Markdown, crawl and map sites, and extract structured data, reached with your Agent200 API key.
About Firecrawl
With the Firecrawl connector, your agent turns websites into clean data: it scrapes a page into Markdown, maps and crawls a whole site, searches the web and extracts structured fields from pages. It is reached with your project’s Agent200 API key, so there is no separate Firecrawl key to collect, store or rotate.
Firecrawl is a web scraping and crawling API that turns websites into LLM-ready Markdown and structured data.
Tools
What your agent can do in Firecrawl.
Each tool is a capability the model can call. You decide which ones a project allows, and your Agent200 API key reaches them.
-
Scrape a page
Readfirecrawl_scrape_pageRead one URL as clean Markdown, HTML or a screenshot.
-
Map a site
Readfirecrawl_map_siteList the URLs of a website.
-
Start a crawl
Readfirecrawl_start_crawlCrawl a website from a starting URL, with path and depth limits.
-
Get crawl results
Readfirecrawl_get_crawlRead the status and pages of a crawl.
-
Search the web
Readfirecrawl_search_webSearch the web and get the content of the results.
-
Extract data
Readfirecrawl_extract_dataPull structured fields from pages, following a schema or a prompt.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in Firecrawl, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Allow
firecrawl_scrape_pagefor single pages, and switch offfirecrawl_start_crawlif your agent should never crawl a whole site. -
Restrict what the agent reaches
Choose the endpoints a project may use. A call outside them is refused.
Get started
Connect Firecrawl
in two steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Run with the Firecrawl tools
Name the model and the tools. The model decides which Firecrawl tools to call, and Agent200 executes them with your Agent200 API key.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "Read the pricing page of this site and list the plans", tools: ["firecrawl"], }); console.log(result.output);
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Firecrawl connector and how to use it.
Connector: Firecrawl, through Agent200. In code: "firecrawl". What it does: Scrape pages into Markdown, crawl and map sites, and extract structured data, reached with your Agent200 API key. Page: https://www.agent200.com/tools/firecrawl/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Agent200 reaches Firecrawl with the project's Agent200 API key. No separate Firecrawl key is needed. 3. Read tools: firecrawl_scrape_page, firecrawl_map_site, firecrawl_start_crawl, firecrawl_get_crawl, firecrawl_search_web, firecrawl_extract_data. Name "firecrawl" in the tools of a request; the model decides which tool to call. 4. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 5. Before a write, confirm with the user, unless they asked for that exact change. 6. For setup with a specific framework, follow its guide: https://www.agent200.com/tools/firecrawl/framework/claude/ https://www.agent200.com/tools/firecrawl/framework/chatgpt/ https://www.agent200.com/tools/firecrawl/framework/claude-code/ https://www.agent200.com/tools/firecrawl/framework/muse/ https://www.agent200.com/tools/firecrawl/framework/grok-bot/ https://www.agent200.com/tools/firecrawl/framework/openai-dots/ https://www.agent200.com/tools/firecrawl/framework/claude-duet/ https://www.agent200.com/tools/firecrawl/framework/hermes-agent/ https://www.agent200.com/tools/firecrawl/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /tools/firecrawl.md
Guides
Use Firecrawl with the AI you build on.
Step-by-step setup for Firecrawl with a specific model, assistant or agent framework.
-
Firecrawl + Claude
How to connect Firecrawl to Claude
-
Firecrawl + ChatGPT
How to connect Firecrawl to ChatGPT
-
Firecrawl + Claude Code
How to connect Firecrawl to Claude Code
-
Firecrawl + Muse
How to connect Firecrawl to Muse
-
Firecrawl + Grok Bot
How to connect Firecrawl to Grok Bot
-
Firecrawl + OpenAI Dots
How to connect Firecrawl to OpenAI Dots
-
Firecrawl + Claude Duet
How to connect Firecrawl to Claude Duet
-
Firecrawl + Hermes Agent
How to connect Firecrawl to Hermes Agent
-
Firecrawl + OpenClaw
How to connect Firecrawl to OpenClaw
FAQ
Firecrawl and Agent200, answered.
Do I need my own Firecrawl API key?
No. Your Agent200 API key reaches Firecrawl, so there is no separate provider key to collect, store or rotate.
Can I limit what my agent can do in Firecrawl?
Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.