imugi_serve · Imugi MCP: Risk & Policy

WHAT IT DOES

What imugi_serve does on Imugi

AI agents invoke imugi_serve to trigger actions in Imugi. 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 imugi_serve needs a policy

Starting a dev server is an Execute action because it triggers an external operation (server startup) whose effects depend on the environment and arguments. While the tool itself does not modify production data or run arbitrary user code, it does launch and manage a subprocess with side effects (network binding, resource consumption, file serving).

From the tool's definition Tool description states 'Start a dev server and return the URL' — this initiates and runs an external process (a development server) whose lifecycle is managed by the MCP session.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

imugi_serve Rate-limited

imugi_serve 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": {
    "imugi_serve": {
      "limits": [
        {
          "counter": "imugi_serve_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 Imugi, so you can run agents against it safely.

FAQ

Questions about imugi_serve

What does the imugi_serve tool do? +

Start a dev server and return the URL (for use with imugi_capture). The server process is tracked and will be cleaned up when the MCP session ends. It is categorised as a Execute tool in the Imugi MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on imugi_serve? +

Register the Imugi MCP server in PolicyLayer and add a rule for imugi_serve: 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 Imugi. Nothing to install.

What risk level is imugi_serve? +

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

Can I rate-limit imugi_serve? +

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

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

imugi_serve is provided by the Imugi MCP server (m00n7682/imugi). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.