AI agents call deep_crawl_site to retrieve information from Crawl-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and extracts web content from sites without modifying data. It falls under Read category. Severity is medium rather than low because deep/recursive crawling across a site could cause denial-of-service impacts on the target server if misused by an AI agent without rate limiting awareness, and may violate robots.txt or terms of service.
From the tool's definition Tool name 'deep_crawl_site' combined with server context showing crawl4ai wrapping for 'extraction and analysis of content from web pages' indicates data retrieval. Sibling tools like 'crawl_url' and 'batch_crawl' confirm this is a Read operation.
Documented attack patterns abuse exactly the kind of access deep_crawl_site gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crawl-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for deep_crawl_site:
{
"version": "1",
"default": "deny",
"tools": {
"deep_crawl_site": {}
}
}deep_crawl_site is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
deep_crawl_site. It is categorised as a Read tool in the Crawl-MCP MCP Server, which means it retrieves data without modifying state.
Register the Crawl- MCP server in PolicyLayer and add a rule for deep_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 Crawl-MCP. Nothing to install.
deep_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 deep_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 deep_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.
deep_crawl_site is provided by the Crawl- MCP server (walksoda/crawl-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 19 Crawl-MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
19 Crawl-MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.