Available

Firecrawl MCP server

Firecrawl crawls websites and extracts structured content at scale, used to gather data for search, research, and indexing by teams building AI and data products. Connect through Arc0 to use the actions your identity is allowed to call.

Web data and scrapingAPI keyMCP + RESTfirecrawl.dev
AUDIT LOG · FIRECRAWLPOLICY: acme-support
09:41:07 · claude · u_8f2read
firecrawl.search
Search the web✓ allowed · 212ms
09:41:08 · claude · u_8f2read
firecrawl.map_site
Map a website✓ allowed · 164ms
09:41:09 · claude · u_8f2write
firecrawl.start_crawl
Start a crawl✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
firecrawl.cancel_crawl
Cancel a crawl✕ blocked · policy: deny
ILLUSTRATIVE POLICY TRACE · NOT A LIVE RECEIPT
01 · USE CASES

Agent workflows for Firecrawl.

01

Scrape a web page

Fetch one public web page or PDF via Firecrawl as markdown, a summary, links or extracted JSON. Use when the user wants the content of a specific URL; not for whole sites (start_crawl). No X or LinkedIn URLs. 1 credit, +4 with extract, +1 per PDF page, +2 if the team has threat scans.

02

Search the web

Search the web or news through Firecrawl and return result URLs, titles and snippets (up to 20). Use when the user needs to find pages about a topic before reading them. Not for fetching a known URL (use scrape_url). Costs 2 credits per 10 results.

03

Map a website

List the URLs of a website (up to 1,000), optionally ranked by a search term, without scraping them. Use when the user wants to see what pages a site has or pick pages to scrape. Not for page content (use scrape_url). Costs 1 credit per call.

02 · ACTIONS

8 Firecrawl actions, graded by risk.

These actions come from the Arc0 registry. Your identity, provider permissions and Arc0 policies determine which actions can run.

read

6

Look things up, subject to your permissions.

  • firecrawl.scrape_url
    Scrape a web page

    Fetch one public web page or PDF via Firecrawl as markdown, a summary, links or extracted JSON. Use when the user wants the content of a specific URL; not for whole sites (start_crawl). No X or LinkedIn URLs. 1 credit, +4 with extract, +1 per PDF page, +2 if the team has threat scans.

  • firecrawl.search
    Search the web

    Search the web or news through Firecrawl and return result URLs, titles and snippets (up to 20). Use when the user needs to find pages about a topic before reading them. Not for fetching a known URL (use scrape_url). Costs 2 credits per 10 results.

  • firecrawl.map_site
    Map a website

    List the URLs of a website (up to 1,000), optionally ranked by a search term, without scraping them. Use when the user wants to see what pages a site has or pick pages to scrape. Not for page content (use scrape_url). Costs 1 credit per call.

  • firecrawl.get_crawl_status
    Get crawl status and pages

    Get a Firecrawl crawl status, page counts and up to 5 crawled pages as markdown. Use when checking or reading a crawl from start_crawl; pass nextCursor as cursor for more. If the response is too large, retry with limit 1, then skip that page with cursor + 1. Results expire 24h after completion.

  • firecrawl.get_crawl_errors
    Get crawl errors

    List pages a Firecrawl crawl failed to scrape (network errors, timeouts) and URLs blocked by robots.txt, up to 100 each. Use when a crawl finished with fewer pages than expected. Not for pages that returned 404s; those are in get_crawl_status.

  • firecrawl.get_credit_usage
    Get remaining credits

    Get the Firecrawl team's remaining credits, plan credits and current billing period. Use when the user asks how many credits are left or before starting a large crawl. Free; does not spend credits.

write

1

Create and change things. Allow, or ask the user first.

  • firecrawl.start_crawl
    Start a crawl

    Start an asynchronous Firecrawl crawl of a website (up to 100 pages) and return its crawl id. Use when the user wants many pages of one site, then poll get_crawl_status. No X or LinkedIn sites. 1 credit per page, +1 per parsed PDF page, +2 per URL if the team has threat scans.

destructive

1

Delete, cancel or archive. Ask first, or deny outright.

  • firecrawl.cancel_crawl
    Cancel a crawl

    Cancel a running Firecrawl crawl so it stops crawling and spending credits. Use when the user asks to stop a crawl or it was started by mistake. Pages already crawled stay readable with get_crawl_status. Not reversible.

03 · POLICIES AND AUDIT

Control access to Firecrawl.

Connect the intended Firecrawl account, authorize your AI client and set policies for its tools.

Provider permissions and Arc0 policy both apply. Allow reads, require approval for selected writes, or deny destructive actions. The audit log records execution decisions.

Configure policies and approvals

Example policy choices

  • Read actions: allow where authorized
  • firecrawl.start_crawl: require approval
  • firecrawl.cancel_crawl: deny

Arc0 MCP endpoint: https://api.arc0.ai/mcp

04 · AUTH AND DATA

How Firecrawl connects.

Connect Firecrawl using API key. OAuth grants the provider scopes shown during consent; API keys and other credentials retain the permissions configured at the provider. Arc0 stores credentials in its encrypted vault and does not pass them to the model. Disconnect to remove access through Arc0; revoke a key at the provider to invalidate it there. Token refresh and provider-side revocation depend on the authentication lane and provider.

The connection serves authorized calls through Arc0 MCP and REST. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · AI CLIENTS

Use Firecrawl with your AI client.

Sign in to Arc0 and connect Firecrawl in My apps. Then authorize your AI client separately. It only receives tools and accounts allowed for that identity.

Firecrawl with Claude

Claude Desktop + Claude Code

  1. In Claude Desktop, add Arc0 through the remote MCP settings and use OAuth. Follow the generic remote-client steps if your account’s interface differs.
  2. For Claude Code, run the command below. Open /mcp, select Arc0, and authenticate in your browser. Select your workspace and review access.
  3. Check the connection with claude mcp get arc0.
claude mcp add --transport http --scope user arc0 https://api.arc0.ai/mcp
Full MCP setup and troubleshooting
All apps for Claude
Firecrawl with ChatGPT

ChatGPT on the web

  1. Open Plugins in ChatGPT, select the plus button, then Add custom MCP server.
  2. Name it Arc0, enter the server URL below, and choose OAuth. Use dynamic client registration if asked; no Arc0 API key is needed.
  3. Review the notice and select Create as a plugin. Complete Arc0 sign-in, workspace selection and consent, then install and select the plugin in your conversation. Labels and access vary by account; managed workspaces may require administrator approval.
https://api.arc0.ai/mcp
Full MCP setup and troubleshooting
All apps for ChatGPT
Firecrawl with OpenAI Codex

Codex app + CLI

  1. Run the registration command below. The app and CLI share ~/.codex/config.toml.
  2. Complete browser OAuth, choose your Arc0 workspace, and review access. If authentication does not start, run codex mcp login arc0.
  3. Check codex mcp list, then open a new Codex chat. Inspect an existing arc0 entry before changing it.
codex mcp add arc0 --url https://api.arc0.ai/mcp
Full MCP setup and troubleshooting
All apps for OpenAI Codex
Firecrawl with Cursor

Remote MCP setup

  1. Add Arc0 in your client’s remote MCP settings using the server URL below.
  2. Choose OAuth, sign in to Arc0, select the intended workspace and review access.
  3. Confirm the server is connected and start with an allowed read. These are generic remote-MCP steps; consult your client’s settings for its current interface.
https://api.arc0.ai/mcp
Full MCP setup and troubleshooting
All apps for Cursor
Firecrawl with VS Code

Remote MCP setup

  1. Add a remote HTTP MCP server named Arc0 using the URL below.
  2. Use OAuth and finish Arc0 sign-in, workspace selection and consent.
  3. Confirm discovery succeeds before requesting a read. These are generic remote-MCP steps; client UI and availability may differ.
https://api.arc0.ai/mcp
Full MCP setup and troubleshooting
Firecrawl with Any MCP client

Streamable HTTP

  1. Use a client that supports remote MCP over Streamable HTTP. Add the server URL below and choose OAuth.
  2. For a client without OAuth, use a self-bound API key with execute permission in the X-API-Key header. Store it in secret storage or an environment variable, outside source control. Never send both an API key and an OAuth bearer token.
  3. Use the MCP clients guide for the SDK transport example and Embedded identity for business-managed end users.
https://api.arc0.ai/mcp
Full MCP setup and troubleshooting

After setup, ask your agent to find an allowed read action, load its schema, and execute it on the intended account. Check Activity for the receipt. A connected MCP client alone does not confirm a successful provider call.

07 · FAQ

Firecrawl and Arc0, answered.

Q01

Does Firecrawl work with Claude Desktop and Claude Code?

Yes, after connecting the account and authorizing the client. Use Arc0’s remote MCP endpoint with OAuth. Claude Code has a documented registration command; Desktop uses the generic remote-client setup.

Q02

Can I use Firecrawl with OpenAI Codex, ChatGPT and Cursor?

Yes, after connecting the account and authorizing the client. Codex and ChatGPT have setup instructions in Arc0’s MCP clients guide. Cursor uses the generic remote-MCP steps. Tool access remains scoped to the authorized identity.

Q03

Is this the official Firecrawl MCP server?

This is Arc0’s integration page, not a claim of an official Firecrawl server. Arc0 adds a shared connection, policy and audit experience across apps. Consult Firecrawl for its own current MCP offerings.

Q04

Which Firecrawl actions are supported?

8 registry-defined actions: 6 read, 1 write and 1 destructive. Provider permissions, access enablement and Arc0 policy determine what can execute.

Q05

Which permissions does Firecrawl need?

Connect Firecrawl using API key. OAuth grants the provider scopes shown during consent; API keys and other credentials retain the permissions configured at the provider. Arc0 stores credentials in its encrypted vault and does not pass them to the model. Disconnect to remove access through Arc0; revoke a key at the provider to invalidate it there. Token refresh and provider-side revocation depend on the authentication lane and provider.

Q06

Can I restrict writes in Firecrawl?

You can deny write and destructive actions or require approval. Provider scopes and Arc0 action policies are separate controls; a policy does not grant additional provider permissions.

Q07

What does Firecrawl through Arc0 cost?

See Arc0 pricing for current connectivity plans. The provider may require its own subscription or charge per request. Arc0 plan allowances do not make third-party data or paid actions free.

Get started

Plug Firecrawl into your agent.

Firecrawl MCP server: 8 actions including scrape a web page, search the web, map a website. Connect through Arc0.

Free to build · MCP + REST · Audit log on every plan

Firecrawl and its logo are trademarks of their respective owners. Arc0 is not affiliated with or endorsed by Firecrawl.