AI agents use transpose_by_interval 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.
Transposing a score modifies the musical data within a .mscz or .musicxml file, but this change is reversible (can be transposed back), and does not destroy or irreversibly delete content. This qualifies as Write rather than Execute or Destructive.
From the tool's definition Tool name 'transpose_by_interval' indicates modification of musical content (changing pitch of notes). Related tool 'change_tempo' on the same server confirms this server performs reversible edits to MuseScore files.
Attacks that exploit this kind of access
transpose_by_interval. 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 transpose_by_interval: 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.
transpose_by_interval 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 transpose_by_interval 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 transpose_by_interval. 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.
transpose_by_interval 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 →