deep_crawl · Crawl4AI MCP Server MCP: Risk & Policy

WHAT IT DOES

What deep_crawl does on Crawl4AI MCP Server

AI agents invoke deep_crawl to trigger actions in Crawl4AI MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why deep_crawl needs a policy

Deep crawling a website involves executing automated network requests across potentially many pages of an external site. This is an Execute-category action because it triggers external operations (HTTP requests, browser automation) whose scope and effects depend on arguments (target URL, depth). Misuse could cause unintended load on external servers, access restricted content, or consume significant resources.

From the tool's definition 'deep_crawl' with description '深度爬取网站' (deep crawl website) — triggers recursive/multi-page web crawling operations across external sites

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

deep_crawl Rate-limited

deep_crawl stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "deep_crawl": {
      "limits": [
        {
          "counter": "deep_crawl_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Crawl4AI MCP Server, so you can run agents against it safely.

FAQ

Questions about deep_crawl

What does the deep_crawl tool do? +

深度爬取网站。. It is categorised as a Execute tool in the Crawl4AI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on deep_crawl? +

Register the Crawl4AI MCP Server MCP server in PolicyLayer and add a rule for deep_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 Crawl4AI MCP Server. Nothing to install.

What risk level is deep_crawl? +

deep_crawl is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit deep_crawl? +

Yes. Add a rate_limit block to the deep_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.

How do I block deep_crawl completely? +

Set action: deny in the PolicyLayer policy for deep_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.

What MCP server provides deep_crawl? +

deep_crawl is provided by the Crawl4AI MCP Server MCP server (stevenzxs/crawl4ai-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.