Disconnect from MuseScore.
AI agents use disconnect_from_musescore to create or update resources in Mcp Score — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Score environment.
Disconnecting from MuseScore is a reversible operation that modifies the server's state without destroying data or executing arbitrary code. If the connection can be re-established via 'connect_to_musescore', the effect is easily undone. This qualifies as Write (modifies state reversibly) rather than Read (which would be querying status).
From the tool's definition Tool name is 'disconnect_from_musescore' and description states 'Disconnect from MuseScore.' This performs a state change by terminating an active connection to MuseScore, modifying the server's connection state.
Documented attack patterns abuse exactly the kind of access disconnect_from_musescore gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Score, and nothing reaches the server without passing your rules. This is the rule we recommend for disconnect_from_musescore:
{
"version": "1",
"default": "deny",
"tools": {
"disconnect_from_musescore": {
"limits": [
{
"counter": "disconnect_from_musescore_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}disconnect_from_musescore 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.
Free to start. No card required.
Disconnect from MuseScore. It is categorised as a Write tool in the Mcp Score MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Score MCP server in PolicyLayer and add a rule for disconnect_from_musescore: 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 Mcp Score. Nothing to install.
disconnect_from_musescore is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the disconnect_from_musescore 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.
Set action: deny in the PolicyLayer policy for disconnect_from_musescore. 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.
disconnect_from_musescore is provided by the Mcp Score MCP server (tskovlund/mcp-score). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Score, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
18 Mcp Score tools catalogued and risk-classified — across an index of 43,000+ MCP servers.