testgen_tdd_repair · Ruflo MCP: Risk & Policy

WHAT IT DOES

What testgen_tdd_repair does on Ruflo

AI agents invoke testgen_tdd_repair to trigger actions in Ruflo. 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 testgen_tdd_repair needs a policy

The tool spawns a headless process and executes code modifications to repair failing tests. This constitutes execution of external operations (spawning agents/processes) and potentially writing/modifying code. Given it 'spawns a bounded headless' entity (likely a subprocess or agent) and operates within a multi-agent harness environment, the most severe applicable category is Execute.

From the tool's definition "Test-Driven Repair", "Spawns a bounded headless" — the tool spawns processes and executes code to repair failing tests

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

testgen_tdd_repair Rate-limited

testgen_tdd_repair 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": {
    "testgen_tdd_repair": {
      "limits": [
        {
          "counter": "testgen_tdd_repair_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 Ruflo, so you can run agents against it safely.

FAQ

Questions about testgen_tdd_repair

What does the testgen_tdd_repair tool do? +

ADR-175-inspired Test-Driven Repair. Use when you have a failing test and want a verified, bounded-cost fix. Spawns a bounded headless. It is categorised as a Execute tool in the Ruflo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on testgen_tdd_repair? +

Register the Ruflo MCP server in PolicyLayer and add a rule for testgen_tdd_repair: 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 Ruflo. Nothing to install.

What risk level is testgen_tdd_repair? +

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

Can I rate-limit testgen_tdd_repair? +

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

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

testgen_tdd_repair is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.