pg_doctor · Planning Game MCP: Risk & Policy

WHAT IT DOES

What pg_doctor does on Planning Game

AI agents invoke pg_doctor to trigger actions in Planning Game. 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 pg_doctor needs a policy

This tool executes diagnostic operations that probe system state, including credential validation and git operations. While not destructive by itself, it performs active inspections and can trigger side effects (e.g., network calls to Firebase, git commands).

From the tool's definition Tool description states it 'Run[s] comprehensive diagnostics' and 'checks Node.js, Firebase credentials, connectivity, dependencies, user config, version, and git.' The verb 'run' combined with access to sensitive information (Firebase credentials, git state)…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pg_doctor Rate-limited

pg_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": {
    "pg_doctor": {
      "limits": [
        {
          "counter": "pg_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 Planning Game, so you can run agents against it safely.

FAQ

Questions about pg_doctor

What does the pg_doctor tool do? +

Run comprehensive diagnostics on the MCP server: checks Node.js, Firebase credentials, connectivity, dependencies, user config, version, and git. Use this to troubleshoot issues. It is categorised as a Execute tool in the Planning Game MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on pg_doctor? +

Register the Planning Game MCP server in PolicyLayer and add a rule for pg_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 Planning Game. Nothing to install.

What risk level is pg_doctor? +

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

Can I rate-limit pg_doctor? +

Yes. Add a rate_limit block to the pg_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 pg_doctor completely? +

Set action: deny in the PolicyLayer policy for pg_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 pg_doctor? +

pg_doctor is provided by the Planning Game MCP server (planning-game-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.