AI agents use change_tempo 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.
Changing tempo is a reversible modification to musical score metadata, not data retrieval (Read), code execution (Execute), irreversible deletion (Destructive), or financial transaction (Financial). It fits Write. Severity is medium because unintended tempo changes could corrupt a musical composition's intended performance, but the change is reversible and the scope is limited to a single attribute.
From the tool's definition Tool name 'change_tempo' paired with server description stating it 'edit[s]' MuseScore files and supports 'transposition' and other modifications.
Attacks that exploit this kind of access
change_tempo. 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.
Register the Musescore MCP server in PolicyLayer and add a rule for change_tempo: 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.
change_tempo 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 change_tempo 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 change_tempo. 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.
change_tempo 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →