What ChatGPT can do with Firecrawl
Ask your agent in plain language. Each of these maps to a real tool on the server.
- Ask ChatGPT to use the get extract status tool in Firecrawl
- Ask ChatGPT to use the get batch scrape status tool in Firecrawl
- Ask ChatGPT to use the scrape page tool in Firecrawl
- Ask ChatGPT to use the get crawl status tool in Firecrawl
- Ask ChatGPT to use the batch scrape tool in Firecrawl
Add the Firecrawl MCP server to ChatGPT
Run these once. Afterwards, everyone you give access to signs in the same way.
1. Enable Firecrawl in Metorial
In your Metorial portal, enable the Firecrawl MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
2. Add a custom MCP server
On ChatGPT web, open Plugins, select +, then Add custom MCP server.
3. Paste your Metorial MCP URL
Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>), choose OAuth and accept the risk notice.
4. Create and install the plugin
Select Create as a plugin, install it and sign in to load Firecrawl tools.
Give your team Firecrawl in ChatGPT
Once Firecrawl is enabled in Metorial, teammates sign in with SSO and get the same connection in ChatGPT, with only the tools their role allows.
One link covers every app you approve. See how the MCP gateway handles access, roles and audit logs for the whole company.
Firecrawl tools available in ChatGPT
Full descriptions and inputs are on the Firecrawl MCP server page.
- Extract Data: Start a Firecrawl v2 extraction job that uses AI to transform one or more web pages into structured data.
- Map Website: Map a website with Firecrawl v2 and retrieve discovered URLs quickly.
- Crawl Website: Start a Firecrawl v2 crawl job to recursively discover and scrape pages from a website.
- Get Agent Status: Check a Firecrawl agent job and retrieve gathered data when complete.
- Run Agent: Start a Firecrawl v2 agent job for autonomous web data gathering.
- Get Extract Status: Check a Firecrawl extract job and retrieve structured data when complete.
- Get Batch Scrape Status: Check a Firecrawl batch scrape job and retrieve available page data.
- Scrape Page: Scrape a single URL with Firecrawl v2 and extract markdown, HTML, raw HTML, links, screenshots, images, audio/video URLs, structured JSON, summaries, brand data, answers, highligh…
- Get Crawl Status: Check a Firecrawl crawl job and retrieve available page data.
- Batch Scrape: Start a Firecrawl v2 batch scrape job for a known list of URLs.
- Search Web: Search the web with Firecrawl v2 and optionally scrape search results.
- Get Crawl Errors: Retrieve failed URLs and robots.txt blocked URLs for a Firecrawl crawl job.
- Parse File: Upload a file to Firecrawl v2 Parse and convert it into markdown or other extraction formats.
- Cancel Crawl: Cancel a running Firecrawl crawl job.
- Interact With Page: Continue interacting with the browser state from a prior Firecrawl scrape.
- And 25 more on the Firecrawl MCP server page.
Using Firecrawl tools in ChatGPT
What to expect once Firecrawl is connected.
- Type @ and pick the plugin. The selection applies to that message only, so @mention it again when a follow-up needs fresh Firecrawl data.
- For write actions, ChatGPT may ask you to confirm first, depending on the app permissions and the action.
- Once published for a workspace, ChatGPT keeps a snapshot of the tool list. When your team adds Firecrawl tools in Metorial, an admin refreshes the actions in Workspace settings before they appear.
- You can use several apps in one prompt, for example read Firecrawl data and then create a ticket in another app.
Troubleshooting ChatGPT
- Add custom MCP server is missing
- Workspace policy controls it. On Enterprise and Edu, an admin grants the permission to create plugins with MCPs; ask them to enable it for you.
- The plugin exists but no tools appear
- Creating the plugin is not enough: install it from your plugins, then start a new conversation so ChatGPT loads its tools.
- ChatGPT answers without using the tools
- Pick the plugin with @ in the composer and name the action you want, for example "use Metorial to look up the latest ticket".
Based on the ChatGPT MCP documentation.
Frequently asked questions
Common questions about connecting Firecrawl to AI agents with Metorial.
Does ChatGPT support the Firecrawl MCP server?
Yes. ChatGPT connects to the Firecrawl MCP server through its connector settings, pointed at your Metorial URL. You need a ChatGPT plan or workspace that allows custom MCP servers.Do I need an API key to connect Firecrawl to ChatGPT?
No. You sign in to Firecrawl once through Metorial, and ChatGPT uses that connection. No API keys go into ChatGPT's settings.Which Firecrawl tools can ChatGPT use?
All 40 Firecrawl tools your team allows, such as Extract Data, Map Website, Crawl Website. Admins can narrow that list per team.Can I control which teammates use Firecrawl in ChatGPT?
Yes. Role-based access control decides who can use Firecrawl and which of its tools appear in ChatGPT, and every call is logged with the person's identity.What if ChatGPT doesn't show Firecrawl tools?
Workspace policy controls it. On Enterprise and Edu, an admin grants the permission to create plugins with MCPs; ask them to enable it for you.
GitHub