run_go_command · Project Creator MCP: Risk & Policy

WHAT IT DOES

What run_go_command does on Project Creator MCP

AI agents invoke run_go_command to trigger actions in Project Creator 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_go_command needs a policy

This tool executes arbitrary Go commands, which can trigger external operations with side effects that depend on the command arguments provided. While not inherently destructive or financial, execution of arbitrary commands poses significant risk if an AI agent provides malicious or unintended commands (e.g., installing dependencies that have side effects, running build scripts, executing tests that modify state).

From the tool's definition Tool name 'run_go_command' combined with server description mentioning 'command execution capabilities' strongly indicates this tool executes Go commands.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_go_command Rate-limited

run_go_command 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_go_command": {
      "limits": [
        {
          "counter": "run_go_command_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 Project Creator MCP, so you can run agents against it safely.

FAQ

Questions about run_go_command

What does the run_go_command tool do? +

run_go_command. It is categorised as a Execute tool in the Project Creator 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_go_command? +

Register the Project Creator MCP server in PolicyLayer and add a rule for run_go_command: 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 Project Creator MCP. Nothing to install.

What risk level is run_go_command? +

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

Can I rate-limit run_go_command? +

Yes. Add a rate_limit block to the run_go_command 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_go_command completely? +

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

run_go_command is provided by the Project Creator MCP server (jackalterman/project-creator-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.