根据用户喜好获取音乐推荐
AI agents call get_recommendations to retrieve information from Claude Music MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries music recommendations based on user preferences and input parameters (genre, mood, etc.). It has no side effects on data—it does not create, modify, delete, or execute external operations. It purely returns data to the user, consistent with Read category tools like search, list, get, and fetch.
From the tool's definition Tool name 'get_recommendations' and description '根据用户喜好获取音乐推荐' (get music recommendations based on user preferences) indicates retrieval of recommendation data with no modification or deletion of data.
Attacks that exploit this kind of access
根据用户喜好获取音乐推荐. It is categorised as a Read tool in the Claude Music MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Music MCP server in PolicyLayer and add a rule for get_recommendations: 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 Claude Music MCP. Nothing to install.
get_recommendations 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_recommendations 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_recommendations. 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_recommendations is provided by the Claude Music MCP server (leehave/claude-music-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 →