Sign in Book a demo
Back to Tools
Developer Tools API Key BYOCPro
Build Your Agent View Firecrawl Docs
firecrawl logo

Firecrawl MCP Tools for AI Agents

Let an agent search the web, read known pages, crawl sites, and extract structured records from plain-language instructions.

Available Tools

19 tools available in this integration

Firecrawl.CancelCrawl

Stop a crawl that is still running.

Firecrawl.CrawlWebsite

Read many pages of one website and return each page's content.

Firecrawl.ExtractData

Collect structured records from the web from a plain-language description.

Firecrawl.ExtractRecords

Collect structured records from the web from a plain-language description.

Firecrawl.GetCrawlData

Read the pages a crawl has collected so far.

Firecrawl.GetCrawlStatus

Check how far a crawl has progressed, without fetching its pages.

Firecrawl.GetExtractStatus

Collect the results of an extraction that is already running.

Firecrawl.GetWebPage

Read one web page whose URL is already known and return its content.

Firecrawl.ListCrawlPages

Read the pages a crawl has collected so far.

Firecrawl.ListWebsiteUrls

List the URLs on a website, without reading the pages.

Firecrawl.MapWebsite

List the URLs on a website, without reading the pages.

Firecrawl.ScrapeUrl

Read one web page whose URL is already known and return its content.

Firecrawl.Search

Search the web and optionally read each result page in the same call.

Firecrawl.SearchDeveloperDocs

Search developer documentation and repositories, quoting the text that matched.

Firecrawl.SearchDeveloperDocuments

Search developer documentation and repositories, quoting the text that matched.

Firecrawl.SearchGithubIssues

Search GitHub issues across indexed repositories.

Firecrawl.SearchResearchPapers

Search published scientific papers and return their abstracts.

Firecrawl.SearchWebPages

Search the web and optionally read each result page in the same call.

Firecrawl.StartCrawl

Read many pages of one website and return each page's content.

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "find the current pricing and API limits for this service and cite the relevant pages." Arcade picks the right Firecrawl tools without guessing whether to search, map, crawl, or extract first.

Up to 100x fewer tokens

Firecrawl search and mapping can return compact results before the agent fetches page content, so it can choose relevant sources without loading entire websites into the model.

Complete the workflow end to end

Search for sources, read the pages that matter, crawl a site, extract structured records, and return citations through one toolkit designed around the complete web research task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing Firecrawl

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For Firecrawl, you can implement some of these policies:

Access when tools are listed for a user
  • Hide Firecrawl.CancelCrawl from agents outside the roles your IDP marks as crawl operators, so regular agents cannot stop another team's collection job.
  • Restrict Firecrawl.CrawlWebsite to agents operating under your approved research role, so unreviewed automation cannot collect an entire site.
  • Deny Firecrawl.ExtractData to agents that lack approval to gather structured records from external websites, so broad data collection cannot run under a general-purpose role.
  • Hide Firecrawl.ExtractRecords from agents outside the roles your IDP approves for structured data collection, so general-purpose agents cannot turn public pages into datasets.
  • Restrict Firecrawl.StartCrawl to agents operating under your approved site-research role, so unattended agents cannot launch broad collections across websites.
Pre-execution before each tool call
  • Require human approval before Firecrawl.CancelCrawl runs, so an agent cannot discard an in-progress crawl without an operator's sign-off.
  • Block Firecrawl.CrawlWebsite when its target is outside your domain allowlist, so an agent cannot crawl customer, partner, or internal sites by mistake.
  • Refuse Firecrawl.ExtractData requests that target domains outside your approved sources or ask for personal data, so an agent cannot turn arbitrary websites into people records.
  • Require human approval before Firecrawl.ExtractRecords runs against more than one domain, so an agent cannot assemble a cross-site vendor or people directory without review.
  • Block Firecrawl.StartCrawl when the target resolves to private network space or a domain outside your organization’s allowlist, so an agent cannot probe internal or unapproved sites.
Post-execution after the tool returns
  • Redact Firecrawl.GetCrawlData results for email addresses, phone numbers, access tokens, and other credentials before the page content reaches the model.
  • Strip API keys, session tokens, passwords, and personal contact details from Firecrawl.ScrapeUrl results, so a readable page cannot expose secrets to the model.
  • Deny Firecrawl.Search results when a returned page contains credentials or data under legal hold, so restricted web content never reaches the model.
  • Redact passwords, bearer tokens, private email addresses, and phone numbers from Firecrawl.GetWebPage results before the model sees the page.
  • Deny Firecrawl.ListCrawlPages output when any collected page is marked confidential or under legal hold, so restricted page content cannot enter the model context.
  • Strip API keys, private repository URLs, and credentials from Firecrawl.SearchDeveloperDocuments excerpts before returning matching code or documentation to the model.

How to use Firecrawl with your agent

Connect Firecrawl to an MCP client and give your agent web search, page reading, crawling, and extraction in a few steps. Pick your client below to follow the setup.

Your questions, answered

A Firecrawl MCP server exposes web research and extraction capabilities as structured tools that an AI agent can call through the Model Context Protocol. The agent can search the web, read known pages, crawl sites, search developer resources, and collect structured records.

Firecrawl provides web-reading and extraction capabilities through its own platform. Arcade adds the runtime around them: a shared API key configured once, agent-optimized tools, approval workflows, redaction, scope controls, and access from any supported client.

Arcade agents can search the web, read known pages, map and crawl websites, check crawl progress, collect structured records from plain-language descriptions, search developer documentation and GitHub issues, and search research papers. They can also stop running crawls and retrieve results from ongoing crawl or extraction jobs.

Arcade uses the Firecrawl API key or secret configured for the integration. Firecrawl's account, plan, and key permissions determine what the agent can access; this integration does not use separate per-user OAuth scopes.

No. Firecrawl uses one shared API key or secret configured for the integration rather than requiring each user to connect an individual account. Arcade brokers that credential, and agents never receive it directly.

Yes. Contextual Access policies can require human approval before consequential Firecrawl calls, such as starting or canceling a crawl or launching an extraction job. The call proceeds only after the policy's conditions have been satisfied.

Arcade proxies Firecrawl API calls and does not persist your content as part of normal tool execution. The Firecrawl credential is brokered and stored encrypted at rest, and the model never receives it.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade refreshes access while the configured Firecrawl credential remains valid. If the key is revoked, rotated, expires, or can no longer be used, calls stop until the credential is updated or reconnected.

Firecrawl's plan limits, API-key quotas, crawl and extraction limits, and any search or page-fetch limits still apply through Arcade. Specific limits depend on the Firecrawl account and plan rather than on Arcade.

Ready to actually ship your agent?

Connect your agent to Firecrawl with a shared API key, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the Firecrawl Quickstart