doctor · Mcp Doctor MCP: Risk & Policy

WHAT IT DOES

What doctor does on Mcp Doctor

AI agents invoke doctor to trigger actions in Mcp Doctor. 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 doctor needs a policy

The tool actively scans connections, audits security configurations, and benchmarks latency across all configured MCP servers. These are not passive reads; they involve initiating network connections, probing endpoints, and measuring performance — external operations whose effects depend on the target servers.

From the tool's definition "Run all checks at once: scan connections, audit security, and benchmark latency" — triggers multiple active operations against configured MCP servers

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

doctor Rate-limited

doctor 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": {
    "doctor": {
      "limits": [
        {
          "counter": "doctor_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 Doctor, so you can run agents against it safely.

FAQ

Questions about doctor

What does the doctor tool do? +

Run all checks at once: scan connections, audit security, and benchmark latency for all configured MCP servers. It is categorised as a Execute tool in the Mcp Doctor MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on doctor? +

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

What risk level is doctor? +

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

Can I rate-limit doctor? +

Yes. Add a rate_limit block to the doctor 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 doctor completely? +

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

doctor is provided by the Mcp Doctor MCP server (realwigu/mcp-doctor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.