run_test · Coding MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_test does on Coding MCP Server

AI agents invoke run_test to trigger actions in Coding 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 run_test needs a policy

This tool executes arbitrary test commands specified in project configuration, which could have side effects depending on test suite implementation (file modifications, external service calls, database changes). While typically benign, test execution is an Execute operation with blast radius determined by what test scripts do.

From the tool's definition The tool name 'run_test' and description 'Run project test command' indicate execution of external commands. The server description mentions 'safe command execution', confirming this tool triggers external processes.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_test Rate-limited

run_test 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_test": {
      "limits": [
        {
          "counter": "run_test_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 Coding MCP Server, so you can run agents against it safely.

FAQ

Questions about run_test

What does the run_test tool do? +

Run project test command. It is categorised as a Execute tool in the Coding 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 run_test? +

Register the Coding MCP Server MCP server in PolicyLayer and add a rule for run_test: 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 Coding MCP Server. Nothing to install.

What risk level is run_test? +

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

Can I rate-limit run_test? +

Yes. Add a rate_limit block to the run_test 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_test completely? +

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

run_test is provided by the Coding MCP Server MCP server (kieutrongthien/coding-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.