watch_folder · Musescore MCP: Risk & Policy

WHAT IT DOES

What watch_folder does on Musescore

AI agents invoke watch_folder 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 watch_folder needs a policy

The name 'watch_folder' suggests this tool monitors a directory for changes and likely triggers operations (such as batch conversion or processing) when files appear or change. This constitutes an external operation/trigger behavior, placing it in Execute. However, the description is empty, so confidence is low. It could also be Read (just observing), but 'watch' patterns typically trigger side-effecting workflows.

From the tool's definition Tool name 'watch_folder' with empty description; inferred from name as a filesystem monitoring/watching operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

watch_folder Rate-limited

watch_folder 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": {
    "watch_folder": {
      "limits": [
        {
          "counter": "watch_folder_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 watch_folder

What does the watch_folder tool do? +

watch_folder. 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 watch_folder? +

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

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

Can I rate-limit watch_folder? +

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

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

watch_folder 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.