Start an asynchronous crawl of multiple pages from a starting URL.
AI agents call firecrawl_crawl to retrieve information from Firecrawl MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs web crawling, which is a read operation that fetches and retrieves content from multiple web pages. However, it has medium severity because an asynchronous crawl of multiple pages can consume significant resources, trigger rate limits on target servers, and potentially access sensitive or restricted content at scale. There are no write, execute, or destructive side effects described.
From the tool's definition 'crawl of multiple pages from a starting URL' — retrieves web content; no data modification implied
Attacks that exploit this kind of access
Start an asynchronous crawl of multiple pages from a starting URL. It is categorised as a Read tool in the Firecrawl MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Firecrawl MCP Server MCP server in PolicyLayer and add a rule for firecrawl_crawl: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Firecrawl MCP Server. Nothing to install.
firecrawl_crawl is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the firecrawl_crawl rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for firecrawl_crawl. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
firecrawl_crawl is provided by the Firecrawl MCP Server MCP server (mcma123/firecrawl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →