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.
Agent workflows for Firecrawl.
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.
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.
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.
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
6Look things up, subject to your permissions.
- firecrawl.scrape_urlScrape 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.searchSearch 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_siteMap 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_statusGet 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_errorsGet 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_usageGet 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
1Create and change things. Allow, or ask the user first.
- firecrawl.start_crawlStart 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
1Delete, cancel or archive. Ask first, or deny outright.
- firecrawl.cancel_crawlCancel 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.
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 approvalsExample policy choices
- Read actions: allow where authorized
- firecrawl.start_crawl: require approval
- firecrawl.cancel_crawl: deny
Arc0 MCP endpoint: https://api.arc0.ai/mcp
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
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
- 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.
- For Claude Code, run the command below. Open /mcp, select Arc0, and authenticate in your browser. Select your workspace and review access.
- Check the connection with claude mcp get arc0.
claude mcp add --transport http --scope user arc0 https://api.arc0.ai/mcpFull MCP setup and troubleshootingFirecrawl with ChatGPT
ChatGPT on the web
- Open Plugins in ChatGPT, select the plus button, then Add custom MCP server.
- Name it Arc0, enter the server URL below, and choose OAuth. Use dynamic client registration if asked; no Arc0 API key is needed.
- 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/mcpFull MCP setup and troubleshootingFirecrawl with OpenAI Codex
Codex app + CLI
- Run the registration command below. The app and CLI share ~/.codex/config.toml.
- Complete browser OAuth, choose your Arc0 workspace, and review access. If authentication does not start, run codex mcp login arc0.
- 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/mcpFull MCP setup and troubleshootingFirecrawl with Cursor
Remote MCP setup
- Add Arc0 in your client’s remote MCP settings using the server URL below.
- Choose OAuth, sign in to Arc0, select the intended workspace and review access.
- 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/mcpFull MCP setup and troubleshootingFirecrawl with VS Code
Remote MCP setup
- Add a remote HTTP MCP server named Arc0 using the URL below.
- Use OAuth and finish Arc0 sign-in, workspace selection and consent.
- Confirm discovery succeeds before requesting a read. These are generic remote-MCP steps; client UI and availability may differ.
https://api.arc0.ai/mcpFull MCP setup and troubleshootingFirecrawl with Any MCP client
Streamable HTTP
- Use a client that supports remote MCP over Streamable HTTP. Add the server URL below and choose OAuth.
- 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.
- Use the MCP clients guide for the SDK transport example and Embedded identity for business-managed end users.
https://api.arc0.ai/mcpFull MCP setup and troubleshootingAfter 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.
Firecrawl and Arc0, answered.
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.
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.
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.
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.
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.
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.
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.
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.