treg.to / Catalog / Firecrawl
7 tools · your own account · never metered

Firecrawl: connect your own account

Scrape pages, search the web, map sites, and run bounded crawls or batches. Connect your own Firecrawl account once and your agent uses it from then on, through one treg.to token. Calls on your own connection are never metered.
Start freeSee all 7 toolsAPI docs ↗
$1.00 of free credit once per new verified account · no card · platform tools need no provider signup
7 of 7 tools on this page are live-verified against the provider.
works in
ChatGPTClaudeClaude CodeCodexCursorGrokGemini CLI
What your agent can now do

Firecrawl, one prompt away

AGENT
ChatGPTClaudeClaude CodeCodexCursorGrokGemini CLI
extract clean content from web pages✓
search the open web by meaning or keyword✓
discover the URLs on a website✓
→
▚ treg
$ treg call firecrawl.web.map
✓ 200 · $0.005/success
$ treg call firecrawl.web.crawl
✓ 200 · $0.005-$0.05/success
$ treg call firecrawl.web.scrape
✓ 200 · $0.005/success
$ _
→
FirecrawlYOUR ACCOUNT
Scrape pages, search the web, map sites, and run bounded crawls or batches.
⚒ 7 TOOLS

SEO · https://api.firecrawl.dev

Set up

Set up Firecrawl in Claude Code, Codex or any agent

1Give this to your agent
in your agent's chat
set up treg — https://treg.sciatafrica.com/llms.txt
2Or add the MCP server yourself
claude code
claude mcp add --transport http treg https://treg.sciatafrica.com/mcp

ChatGPT

Settings → Connectors → add https://treg.sciatafrica.com/mcp as a custom connector.

Grok bot

Add https://treg.sciatafrica.com/mcp as a remote MCP connector in its tool settings.

Claude Desktop

Settings → Connectors → Add custom connector → https://treg.sciatafrica.com/mcp.

Cursor, Codex, any MCP client

Point it at https://treg.sciatafrica.com/mcp (HTTP transport).

CLI

curl -fsSL https://treg.sciatafrica.com/install.sh | sh

Plain HTTP

LangChain, CrewAI or any code: /call/<tool-id> + X-Treg-Token: <token>. No SDK.

Try it

What's the best way to ask?

the prompt
Using treg, extract clean content from web pages. Show me the price first.

Run one directly

a live-verified call
treg call firecrawl.web.map --method POST --data '{"url":"https://example.com","limit":5}'
Why treg.to

Why call Firecrawl through treg.to

Your account, held safely

Connect once; treg.to keeps the credential server-side and injects it per call. No key on any machine.

Price before the call

The provider's own rate, $0.000 markup. How billing works.

Account billing

Calls through your own connection are not metered by treg.

Your own Firecrawl key is free

Register it and those calls are never metered. Your key always wins.

Switch by changing a word

Another provider is a different word in the prompt, not a new integration.

One key, the whole catalog

The same token calls AnyAPI, Context.dev, Brave Search and 3,611 other tools.

The shelf

All 7 Firecrawl tools

Open web & SEO data · 7 tools
  • Extract a batch of pages · BYOK only · live-verified · No treg charge; upstream $0.05/success
    Start a bounded batch scrape of up to ten URLs. firecrawl.web.batch-scrape
    A live one-URL batch ended with creditsUsed: 1 and reduced the balance by one credit. The ten-credit hold is a conservative upper bound; terminal usage settles the actual charge.
  • Check a batch scrape · BYOK only · helper · live-verified · No treg charge; upstream free
    Read an owned batch's status, result pages and credit usage. firecrawl.web.batch-scrape.status
    Polling does not consume Firecrawl credits.
  • Crawl a website · BYOK only · live-verified · No treg charge; upstream $0.005-$0.05/success
    Start a bounded crawl and pay for pages processed. firecrawl.web.crawl
    A live one-page crawl ended with creditsUsed: 1 and reduced the balance by one credit. The hold is the requested page limit and terminal usage settles it.
  • Check a website crawl · BYOK only · helper · live-verified · No treg charge; upstream free
    Read an owned crawl's status, result pages and credit usage. firecrawl.web.crawl.status
    Polling does not consume Firecrawl credits.
  • Map a website · BYOK only · live-verified · No treg charge; upstream $0.005/success
    Discover URLs on a website without scraping their content. firecrawl.web.map
    Live one-link, three-link and five-link maps each reduced the balance by one credit; Firecrawl's billing guide states one credit per call.
  • Scrape a web page · BYOK only · live-verified · No treg charge; upstream $0.005/success
    Fetch one page as Markdown, HTML or links. firecrawl.web.scrape
    One basic page costs one credit with parsers: []; a PDF is returned as base64. Firecrawl bills a returned target 403/404 document, but no-document failures are free.
  • Search the open web · BYOK only · live-verified · No treg charge; upstream $0.01/success
    Find up to ten web results without scraping their full pages. firecrawl.web.search
    The live three-result search returned creditsUsed: 2 and the account balance fell by two credits.

Reliability badges come from live traffic through treg.to. Live-verified means a successful provider check; it does not verify every request variant.

Related

Same jobs, other providers

These providers answer some of the same capabilities as Firecrawl. The platform pages show them on one row with rate and coverage; choosing is yours, treg.to does not route between providers automatically.

also on the catalog
AnyAPIContext.devBrave SearchCrawl4AIDiffbotExaKeenableLimaDataLinkupLitescrapeOctenOlostep
Questions

Before you start

Do I need a Firecrawl account?

Yes. This is an own-account connection: you sign in to Firecrawl once and your agent uses that connection through your treg.to token. Calls on it are never metered.

How do I add Firecrawl to Claude Code?

Run: claude mcp add --transport http treg https://treg.sciatafrica.com/mcp. One MCP server carries Firecrawl and the rest of the catalog.

Which frameworks does it work with?

Anything that speaks MCP (Claude Code, Claude Desktop, ChatGPT, Codex, Cursor, Grok) and anything that can make an HTTP request (LangChain, CrewAI, LlamaIndex, plain code).

Is this the official Firecrawl MCP server?

No. treg.to serves Firecrawl's real API through its own metered proxy: the request is the provider's own, the credential is injected server-side, and the answer is relayed verbatim. The official Firecrawl channels are linked above.