deep_scan · Deadlink Checker MCP: Risk & Policy

WHAT IT DOES

What deep_scan does on Deadlink Checker

AI agents invoke deep_scan to trigger actions in Deadlink Checker. 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_scan needs a policy

Recursively crawling a website is an active external operation, not a passive read of stored data. It initiates network requests to third-party systems at scale, which could impact the target server (load, rate limits, detection as a bot). This fits Execute — it triggers external operations whose effects depend on arguments — rather than a simple Read, which would imply a single bounded lookup with no side effects.

From the tool's definition 'Recursively crawl a website' — this triggers an active, ongoing external operation (crawling) that sends potentially many HTTP requests to a target website, whose scope and effects depend on the arguments provided.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

deep_scan Rate-limited

deep_scan 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_scan": {
      "limits": [
        {
          "counter": "deep_scan_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 Deadlink Checker, so you can run agents against it safely.

FAQ

Questions about deep_scan

What does the deep_scan tool do? +

Recursively crawl a website. It is categorised as a Execute tool in the Deadlink Checker 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_scan? +

Register the Deadlink Checker MCP server in PolicyLayer and add a rule for deep_scan: 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 Deadlink Checker. Nothing to install.

What risk level is deep_scan? +

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

Can I rate-limit deep_scan? +

Yes. Add a rate_limit block to the deep_scan 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_scan completely? +

Set action: deny in the PolicyLayer policy for deep_scan. 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_scan? +

deep_scan is provided by the Deadlink Checker MCP server (yifanyifan897645/deadlink-checker-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.