run_tests · Reviewer MCP: Risk & Policy

WHAT IT DOES

What run_tests does on Reviewer MCP

AI agents invoke run_tests to trigger actions in Reviewer 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_tests needs a policy

This tool executes tests, which involves running code whose behavior depends on what tests are defined in the project. While tests are typically benign, they execute arbitrary code in the project repository and could have side effects depending on test implementation (file creation, network calls, etc.). This qualifies as Execute rather than Read since it triggers external operations beyond simple data retrieval.

From the tool's definition Tool description states it 'Run[s] standardized tests for the project' — a direct execution action that triggers external operations (test runners, potentially arbitrary test code).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_tests Rate-limited

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": {
    "run_tests": {
      "limits": [
        {
          "counter": "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 Reviewer MCP, so you can run agents against it safely.

FAQ

Questions about run_tests

What does the run_tests tool do? +

Run standardized tests for the project (with coverage when no pattern specified). It is categorised as a Execute tool in the Reviewer 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_tests? +

Register the Reviewer MCP server in PolicyLayer and add a rule for 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 Reviewer MCP. Nothing to install.

What risk level is run_tests? +

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

Can I rate-limit run_tests? +

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

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

run_tests is provided by the Reviewer MCP server (jaggederest/mcp_reviewer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.