forloop_agent_decision · ForLoop MCP: Risk & Policy

WHAT IT DOES

What forloop_agent_decision does on ForLoop MCP

AI agents invoke forloop_agent_decision to trigger actions in ForLoop 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 forloop_agent_decision needs a policy

While the description lacks detail, the context shows this tool orchestrates decisions within a system that applies patches, runs tests, and performs type-checking on code repositories. Returning 'the next decision' in such a loop suggests it executes conditional logic that triggers downstream operations (repo modifications, tests).

From the tool's definition The tool 'forloop_agent_decision' is described as returning 'the next ForLoop agent decision' in a system that 'enables AI harnesses to run iterative loops on code repositories' with 'approval workflows.' Given the sibling tools include repo.apply_patch, repo.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

forloop_agent_decision Rate-limited

forloop_agent_decision 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": {
    "forloop_agent_decision": {
      "limits": [
        {
          "counter": "forloop_agent_decision_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 ForLoop MCP, so you can run agents against it safely.

FAQ

Questions about forloop_agent_decision

What does the forloop_agent_decision tool do? +

Return the next ForLoop agent decision. It is categorised as a Execute tool in the ForLoop 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 forloop_agent_decision? +

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

What risk level is forloop_agent_decision? +

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

Can I rate-limit forloop_agent_decision? +

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

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

forloop_agent_decision is provided by the ForLoop MCP server (master0ffate/forloop-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.