Discover URLs from a starting point. Can use both sitemap.xml and HTML link discovery.
AI agents call firecrawl_map to retrieve information from Mcp Docs Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and maps the structure of a website to discover URLs. It performs passive discovery and retrieval of information already present on the target site. There are no side effects, data modifications, code execution, or destructive operations.
From the tool's definition Tool name and description indicate it 'Discover URLs from a starting point' using 'sitemap.xml and HTML link discovery' — operations that retrieve and enumerate existing data without modifying, deleting, or executing code.
Attacks that exploit this kind of access
Discover URLs from a starting point. Can use both sitemap.xml and HTML link discovery. It is categorised as a Read tool in the Mcp Docs Server MCP Server, which means it retrieves data without modifying state.
Register the Mcp Docs Server MCP server in PolicyLayer and add a rule for firecrawl_map: 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 Mcp Docs Server. Nothing to install.
firecrawl_map 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_map 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_map. 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_map is provided by the Mcp Docs Server MCP server (@mastra/mcp-docs-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 →