repo.run_tests · ForLoop MCP: Risk & Policy

WHAT IT DOES

What repo.run_tests does on ForLoop MCP

AI agents invoke repo.run_tests 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 repo.run_tests needs a policy

The tool invokes a pre-configured but externally-defined test command, which can execute arbitrary code including network calls, file writes, or other side effects. While constrained to a single configured command (reducing blast radius vs. unrestricted Execute), it still triggers code execution whose actual behavior is opaque to the AI agent.

From the tool's definition Tool description states "Run only the configured test command" — this executes arbitrary code (the test suite) via a shell command, whose effects depend on test implementation and side effects.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

repo.run_tests Rate-limited

repo.run_tests 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": {
    "repo.run_tests": {
      "limits": [
        {
          "counter": "repo.run_tests_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 repo.run_tests

What does the repo.run_tests tool do? +

Run only the configured test command. 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 repo.run_tests? +

Register the ForLoop MCP server in PolicyLayer and add a rule for repo.run_tests: 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 repo.run_tests? +

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

Can I rate-limit repo.run_tests? +

Yes. Add a rate_limit block to the repo.run_tests 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 repo.run_tests completely? +

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

repo.run_tests 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.