lupa_run_tests · Lupa MCP Server MCP: Risk & Policy

WHAT IT DOES

What lupa_run_tests does on Lupa MCP Server

AI agents invoke lupa_run_tests to trigger actions in Lupa MCP Server. 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 lupa_run_tests needs a policy

This tool executes test code whose behavior depends entirely on the test files and their contents. While test execution is typically a development activity, an AI agent misusing this tool could trigger tests that modify system state, access sensitive data, make external requests, or cause other unpredictable effects.

From the tool's definition Tool description states 'Run Lupa tests and return structured JSON results' — the verb 'run' indicates code execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lupa_run_tests Rate-limited

lupa_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": {
    "lupa_run_tests": {
      "limits": [
        {
          "counter": "lupa_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 Lupa MCP Server, so you can run agents against it safely.

FAQ

Questions about lupa_run_tests

What does the lupa_run_tests tool do? +

Run Lupa tests and return structured JSON results. Use this to identify failing tests. It is categorised as a Execute tool in the Lupa MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on lupa_run_tests? +

Register the Lupa MCP Server MCP server in PolicyLayer and add a rule for lupa_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 Lupa MCP Server. Nothing to install.

What risk level is lupa_run_tests? +

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

Can I rate-limit lupa_run_tests? +

Yes. Add a rate_limit block to the lupa_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 lupa_run_tests completely? +

Set action: deny in the PolicyLayer policy for lupa_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 lupa_run_tests? +

lupa_run_tests is provided by the Lupa MCP Server MCP server (pawel-up/lupa-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.