AI agents call list_instruments to retrieve information from Musescore without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or enumerates instruments from a musical score without side effects. It fits the Read category: querying data with no capability to create, modify, delete, or execute external operations. Severity is low because misuse poses minimal risk—an AI could at worst retrieve unwanted instrument information, but cannot alter files or trigger external systems.
From the tool's definition Tool name 'list_instruments' and server context indicate data retrieval. The function queries existing instruments in a MuseScore file without modification.
Attacks that exploit this kind of access
list_instruments. It is categorised as a Read tool in the Musescore MCP Server, which means it retrieves data without modifying state.
Register the Musescore MCP server in PolicyLayer and add a rule for list_instruments: 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.
list_instruments is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_instruments 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 list_instruments. 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.
list_instruments 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 →