start_loop · Dev Loop MCP: Risk & Policy

WHAT IT DOES

What start_loop does on Dev Loop

AI agents invoke start_loop to trigger actions in Dev Loop. 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 start_loop needs a policy

This tool triggers automated code generation, testing, and version control operations that execute complex external workflows. While the description is incomplete ('Returns an instruction telling you' is truncated), the context makes clear this initiates multi-step automated development processes.

From the tool's definition Tool description indicates it 'Start[s] a new TDD development loop' which initiates an automated workflow.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_loop Rate-limited

start_loop 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": {
    "start_loop": {
      "limits": [
        {
          "counter": "start_loop_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 Dev Loop, so you can run agents against it safely.

FAQ

Questions about start_loop

What does the start_loop tool do? +

Start a new TDD development loop. Returns an instruction telling you. It is categorised as a Execute tool in the Dev Loop MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_loop? +

Register the Dev Loop MCP server in PolicyLayer and add a rule for start_loop: 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 Dev Loop. Nothing to install.

What risk level is start_loop? +

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

Can I rate-limit start_loop? +

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

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

start_loop is provided by the Dev Loop MCP server (soynog/dev-loop-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.