tdd_start_watch · Promethean OS MCP: Risk & Policy

WHAT IT DOES

What tdd_start_watch does on Promethean OS MCP

AI agents invoke tdd_start_watch to trigger actions in Promethean OS 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 tdd_start_watch needs a policy

This tool triggers execution of an external process (AVA test runner in watch mode) whose behavior and side effects depend on the test suite being monitored. While the primary intent is testing rather than arbitrary command execution, it still executes code and can trigger cascading effects through the test pipeline.

From the tool's definition Tool description states 'Start an AVA --watch process' which launches an external process that continuously monitors and executes tests. AVA is a test runner that executes arbitrary code.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tdd_start_watch Rate-limited

tdd_start_watch 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": {
    "tdd_start_watch": {
      "limits": [
        {
          "counter": "tdd_start_watch_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 Promethean OS MCP, so you can run agents against it safely.

FAQ

Questions about tdd_start_watch

What does the tdd_start_watch tool do? +

Start an AVA --watch process and stream output via getWatchChanges. It is categorised as a Execute tool in the Promethean OS 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 tdd_start_watch? +

Register the Promethean OS MCP server in PolicyLayer and add a rule for tdd_start_watch: 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 Promethean OS MCP. Nothing to install.

What risk level is tdd_start_watch? +

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

Can I rate-limit tdd_start_watch? +

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

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

tdd_start_watch is provided by the Promethean OS MCP server (octave-commons/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.