search.crawl · MCP: Risk & Policy

WHAT IT DOES

What search.crawl does on Mcp

AI agents invoke search.crawl to trigger actions in Mcp. 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 search.crawl needs a policy

Crawling is not a passive read; it initiates repeated outbound HTTP requests to external systems, following links programmatically. This constitutes executing an external operation whose scope and side effects depend on the arguments (url, limit, maxDepth, instructions). Misuse could trigger rate-limiting, scrape private/internal sites, or cause unintended load on targets.

From the tool's definition 'Crawl a site and return clean page content... Follows links from the start URL (up to 10 pages, depth ≤2)' — actively traverses and fetches multiple external URLs, triggering network requests against third-party sites

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

search.crawl Rate-limited

search.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": {
    "search.crawl": {
      "limits": [
        {
          "counter": "search.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 Mcp, so you can run agents against it safely.

FAQ

Questions about search.crawl

What does the search.crawl tool do? +

Crawl a site and return clean page content. POST { url, limit?, maxDepth?, instructions? }. Follows links from the start URL (up to 10 pages, depth ≤2) and returns each page\. It is categorised as a Execute tool in the Mcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on search.crawl? +

Register the MCP server in PolicyLayer and add a rule for search.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 Mcp. Nothing to install.

What risk level is search.crawl? +

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

Can I rate-limit search.crawl? +

Yes. Add a rate_limit block to the search.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 search.crawl completely? +

Set action: deny in the PolicyLayer policy for search.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 search.crawl? +

search.crawl is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.