# Any page. Ready for your agent.

Source: https://corespeed.io/integrations/firecrawl

Connect Firecrawl to Claude Code, Codex, Cursor or any MCP agent through CoreSpeed. Your agent turns a URL into clean Markdown, maps the pages of a site, crawls a whole section, and parses a PDF into text or structured fields. It uses the Firecrawl API key you paste once, and each operation spends your own Firecrawl credits.

## Set up an agent

Give your agent this line: `set up https://corespeed.io/SKILL.md (read it raw, e.g. with curl)`

It fetches the skill at https://corespeed.io/SKILL.md, adds the CoreSpeed MCP server, signs you in (or up), and keeps the skill for next time. Connect Firecrawl after setup. Access follows the connected account and its permissions. Create an account: https://app.corespeed.io/sign-up

## Point at a site. Get the part you need

Have your agent map a site, pick the pages that answer your question, and read them as Markdown.

You ask your agent: "Map the docs at docs.example.com, read the page about authentication, and list every way a client can sign in."

It calls CoreSpeed:

- `firecrawl__map`: ok, 1630 ms
- `firecrawl__scrape`: ok, 2140 ms

It reads from: Firecrawl.

### Docs summary: Three ways to sign in.

The docs describe OAuth, API keys and single sign-on. API keys are per team.

**Sign-in methods**

- OAuth 2.0 with PKCE.
- Team API keys.
- SAML single sign-on on paid plans.

**Not covered**

- How keys are rotated.

_Illustrative site and pages · One page read_

All connectors: https://corespeed.io/docs/connectors

## Less copy and paste. Cleaner context

Requests you can make once Firecrawl is connected. The data is fictional.

### Read one page

A changelog, as Markdown · Scrape

- From: One changelog page
- To: Headings and lists, no menus
- Clean text for your agent

### See a site’s pages

The docs, mapped · Map

- Site: docs.example.com
- Found: 142 pages, 9 about auth
- A list of links · Nothing crawled yet

### Find it, then read it

Search first, then crawl · Firecrawl + Exa

- Exa: Finds the right site
- Firecrawl: Reads its pages in full
- With a second connection

Full example: https://corespeed.io/integrations/exa (Markdown: https://corespeed.io/integrations/exa.md)

## Keep your agent. Bring your work

One CoreSpeed account, across compatible agents.

1. **Set up CoreSpeed**: Give your agent the setup line. It adds CoreSpeed and signs you in.
2. **Connect Firecrawl**: Authorize the account and the content you need.
3. **Start with one task**: Ask for a summary, a brief, or a draft. Review the answer.

Setup guides: Claude Code https://corespeed.io/docs/mcp#claude-code · Codex https://corespeed.io/docs/mcp#codex · Cursor https://corespeed.io/docs/mcp#cursor

## Questions

### Do I need my own Firecrawl account?

Yes. Paste a Firecrawl API key once in CoreSpeed. Your agents call Firecrawl without holding the key, and each operation spends your Firecrawl credits.

### How does a crawl of a large site work?

A crawl or batch scrape starts as a job. Your agent checks the job’s status and reads the results page by page.

### Can it read PDFs and other documents?

Yes. Your agent uploads the document, and Firecrawl returns it as Markdown or structured output.

### Do I have to switch agents?

No. CoreSpeed adds tools to the agent you already use: Claude Code, Codex, Cursor, or another MCP client. Each one signs in once.

### Can my agent access every account in our organization?

No. Access follows your CoreSpeed identity, each connection's visibility, and the app's own permissions. Personal connections stay private.

### Does this work without connecting an account?

No. Connect the app's account first; your CoreSpeed workspace shows what each app needs. The examples on this page use fictional data. All connectors: https://corespeed.io/docs/connectors

Every tool and price: https://corespeed.io/catalog/firecrawl

## Related pages

- [Apify for Claude Code, Codex, and Cursor](https://corespeed.io/integrations/apify): Find an Apify Actor, run it, and read its dataset from the agent you already use, on your own Apify account.
- [Exa for Claude Code, Codex, and Cursor](https://corespeed.io/integrations/exa): Search the web with Exa, read the pages that matter, and get cited answers inside the agent you already use.
- [MCP gateway for your agents and tools](https://corespeed.io/solutions/mcp-gateway): Reach connected apps, built-in tools, and your own remote MCP servers through one authenticated CoreSpeed MCP endpoint.

## Sources

- Connectors: https://corespeed.io/docs/connectors
- Firecrawl scrape: https://docs.firecrawl.dev/features/scrape
- Firecrawl crawl: https://docs.firecrawl.dev/features/crawl
- Firecrawl map: https://docs.firecrawl.dev/features/map
- Firecrawl parse: https://docs.firecrawl.dev/api-reference/endpoint/parse

Reviewed 2026-11-10.

## Links

- Product overview: https://corespeed.io/ (Markdown: https://corespeed.io/index.md)
- All integrations: https://corespeed.io/integrations (Markdown: https://corespeed.io/integrations.md)
- Documentation: https://corespeed.io/docs
- Pricing: https://corespeed.io/pricing (Markdown: https://corespeed.io/pricing.md)