run_plugin · Musescore MCP: Risk & Policy

WHAT IT DOES

What run_plugin does on Musescore

AI agents invoke run_plugin to trigger actions in Musescore. 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_plugin needs a policy

The name 'run_plugin' alone signals code execution capability. Without a description limiting scope, this tool can trigger arbitrary plugin logic in the MuseScore ecosystem, which may modify files, execute scripts, or perform uncontrolled operations. This falls into Execute rather than Destructive because the actual destructive impact depends on which plugin is invoked.

From the tool's definition Tool name 'run_plugin' indicates execution of arbitrary plugins with no description provided to constrain behavior.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_plugin Rate-limited

run_plugin 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_plugin": {
      "limits": [
        {
          "counter": "run_plugin_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 Musescore, so you can run agents against it safely.

FAQ

Questions about run_plugin

What does the run_plugin tool do? +

run_plugin. It is categorised as a Execute tool in the Musescore 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_plugin? +

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

What risk level is run_plugin? +

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

Can I rate-limit run_plugin? +

Yes. Add a rate_limit block to the run_plugin 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_plugin completely? +

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

run_plugin is provided by the Musescore MCP server (strongbeen04/musescore-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.