Discover pages from the sitemap and return a compact content summary (title, meta description, top headings, and a short text excerpt) for each. Respects robots.txt. Returns one small object per page so many pages fit in a model
AI agents call crawl_pages to retrieve information from Mcp Bot Crawler without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries publicly available page content metadata without modifying, deleting, executing code, or triggering side effects. It is a straightforward Read operation with minimal security risk. The low severity reflects that it only accesses public sitemap data that is already intended for discovery, and the high confidence reflects the clear informational nature of the operation.
From the tool's definition Tool performs discovery and retrieval of page metadata (title, meta description, headings, excerpt) from sitemaps. Action verbs are 'Discover' and 'return'.
Attacks that exploit this kind of access
Discover pages from the sitemap and return a compact content summary (title, meta description, top headings, and a short text excerpt) for each. Respects robots.txt. Returns one small object per page so many pages fit in a model. It is categorised as a Read tool in the Mcp Bot Crawler MCP Server, which means it retrieves data without modifying state.
Register the Mcp Bot Crawler MCP server in PolicyLayer and add a rule for crawl_pages: 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 Bot Crawler. Nothing to install.
crawl_pages 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_pages 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_pages. 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_pages is provided by the Mcp Bot Crawler MCP server (merulocal/hellogrowthcrmwebsite_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 →