AI agents call crawl_site to retrieve information from Crawler without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves web content by traversing links within a site's structure. It performs queries/fetches of existing data with configurable limits to prevent excessive requests. The worst-case misuse would be excessive bandwidth consumption on a target server, but the tool itself does not modify, delete, or execute code.
From the tool's definition Tool description states it 'recursively crawl[s] a website starting from a URL, following links' with limits on depth and page count. The verb 'crawl' in web contexts means to fetch and retrieve content without modification.
Attacks that exploit this kind of access
Recursively crawl a website starting from a URL, following links up to a maximum depth and page count. It is categorised as a Read tool in the Crawler MCP Server, which means it retrieves data without modifying state.
Register the Crawler MCP server in PolicyLayer and add a rule for crawl_site: 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 Crawler. Nothing to install.
crawl_site 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 crawl_site 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 crawl_site. 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.
crawl_site is provided by the Crawler MCP server (shadab15github/crawler-mcp). 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 →