midi_to_score · Musescore MCP: Risk & Policy

WHAT IT DOES

What midi_to_score does on Musescore

AI agents use midi_to_score to create or update resources in Musescore — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Musescore environment.

WHY IT NEEDS A POLICY

Why midi_to_score needs a policy

The tool creates or generates a new MuseScore file from MIDI data, which is a reversible write operation. It does not execute arbitrary code or permanently delete data. While format conversion tools can have side effects depending on arguments (e.g., quality loss during conversion), the core action is creation/modification of music files rather than destructive deletion or dangerous command execution.

From the tool's definition Tool name 'midi_to_score' indicates conversion/creation of a music score from MIDI input. This aligns with sibling tools like 'create_from_musicxml' and 'convert_score' which perform data creation/transformation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

midi_to_score Rate-limited

midi_to_score stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "midi_to_score": {
      "limits": [
        {
          "counter": "midi_to_score_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 midi_to_score

What does the midi_to_score tool do? +

midi_to_score. It is categorised as a Write tool in the Musescore MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on midi_to_score? +

Register the Musescore MCP server in PolicyLayer and add a rule for midi_to_score: 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 midi_to_score? +

midi_to_score is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit midi_to_score? +

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

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

midi_to_score 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.