mcp_run_pytest · Local Code MCP: Risk & Policy

WHAT IT DOES

What mcp_run_pytest does on Local Code

AI agents invoke mcp_run_pytest to trigger actions in Local Code. 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 mcp_run_pytest needs a policy

The tool runs an external process (pytest) whose behavior depends entirely on the test suite's implementation. While pytest is typically safe in development contexts, a malicious or compromised test file could read secrets, exfiltrate data, modify files, or trigger other side effects.

From the tool's definition Tool description explicitly states 'Run python -m pytest' — this executes a test runner process. Although pytest is a testing framework, the tool triggers arbitrary command execution within an allowed project root, and test code can perform side effects (file…

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mcp_run_pytest Rate-limited

mcp_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": {
    "mcp_run_pytest": {
      "limits": [
        {
          "counter": "mcp_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 Local Code, so you can run agents against it safely.

FAQ

Questions about mcp_run_pytest

What does the mcp_run_pytest tool do? +

Run python -m pytest in an allowed project root. It is categorised as a Execute tool in the Local Code MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mcp_run_pytest? +

Register the Local Code MCP server in PolicyLayer and add a rule for mcp_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 Local Code. Nothing to install.

What risk level is mcp_run_pytest? +

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

Can I rate-limit mcp_run_pytest? +

Yes. Add a rate_limit block to the mcp_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 mcp_run_pytest completely? +

Set action: deny in the PolicyLayer policy for mcp_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 mcp_run_pytest? +

mcp_run_pytest is provided by the Local Code MCP server (js190-prog/local-code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.