Get songs from the user
AI agents call get_library_songs to retrieve information from Apple Music MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries the user's library songs without creating, modifying, deleting, or executing any operations. It is a straightforward read operation on personal music library data. The low severity reflects minimal security risk, as it only exposes existing user data that the authenticated user already owns.
From the tool's definition Tool name 'get_library_songs' and description 'Get songs from the user' indicate data retrieval with no modifications or side effects.
Attacks that exploit this kind of access
Get songs from the user. It is categorised as a Read tool in the Apple Music MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Apple Music MCP Server MCP server in PolicyLayer and add a rule for get_library_songs: 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 Apple Music MCP Server. Nothing to install.
get_library_songs 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 get_library_songs 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 get_library_songs. 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.
get_library_songs is provided by the Apple Music MCP Server MCP server (popand/applemusicmcp). 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 →