run_pytest · Debug Companion MCP: Risk & Policy

WHAT IT DOES

What run_pytest does on Debug Companion MCP

AI agents invoke run_pytest to trigger actions in Debug Companion 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 run_pytest needs a policy

Running pytest executes arbitrary Python test code whose behavior depends on the test suite contents. While pytest itself is a legitimate testing tool, an AI agent misusing run_pytest could execute malicious code hidden in test files, modify application state during test runs, or trigger side effects in test fixtures and setup/teardown code.

From the tool's definition The server enables 'running pytest' and the tool name 'run_pytest' indicates execution of the pytest test runner. The sibling tools 'debug_project', 'extract_failures', and 'open_context' confirm this is a testing/debugging framework that executes code.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_pytest Rate-limited

run_pytest 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": {
    "run_pytest": {
      "limits": [
        {
          "counter": "run_pytest_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 Debug Companion MCP, so you can run agents against it safely.

FAQ

Questions about run_pytest

What does the run_pytest tool do? +

run_pytest. It is categorised as a Execute tool in the Debug Companion 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 run_pytest? +

Register the Debug Companion MCP server in PolicyLayer and add a rule for run_pytest: 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 Debug Companion MCP. Nothing to install.

What risk level is run_pytest? +

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

Can I rate-limit run_pytest? +

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

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

run_pytest is provided by the Debug Companion MCP server (shanirap/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.