advance_loop · Dev Loop MCP: Risk & Policy

WHAT IT DOES

What advance_loop does on Dev Loop

AI agents invoke advance_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 advance_loop needs a policy

This tool drives a state machine through its lifecycle stages, triggering subsequent operations (tests, code generation, PR creation) based on reported outcomes. It acts as an execution controller — its effects depend on the current state and arguments, and it can trigger external operations like automated pull requests.

From the tool's definition 'advance_loop' within an 'AI-driven TDD state machine' that 'handles everything from task decomposition and test-driven development to integration testing and automated pull request creation'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

advance_loop Rate-limited

advance_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": {
    "advance_loop": {
      "limits": [
        {
          "counter": "advance_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 advance_loop

What does the advance_loop tool do? +

Report the outcome of the last instruction and get the next one. 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 advance_loop? +

Register the Dev Loop MCP server in PolicyLayer and add a rule for advance_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 advance_loop? +

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

Can I rate-limit advance_loop? +

Yes. Add a rate_limit block to the advance_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 advance_loop completely? +

Set action: deny in the PolicyLayer policy for advance_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 advance_loop? +

advance_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.