recommend_tracks
AI agents call recommend_tracks to retrieve information from TIDAL MCP: My Custom Picks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Recommending tracks is fundamentally a retrieval operation that queries TIDAL's recommendation engine and returns music suggestions. It does not create, modify, delete, or execute external operations—it only reads and presents data. The tool poses minimal risk of misuse; an AI agent calling it repeatedly would simply receive many recommendations without side effects.
From the tool's definition Tool name 'recommend_tracks' and server context describing 'personalized music recommendations from TIDAL' indicate a read/query operation that retrieves recommended tracks.
Attacks that exploit this kind of access
recommend_tracks. It is categorised as a Read tool in the TIDAL MCP: My Custom Picks MCP Server, which means it retrieves data without modifying state.
Register the TIDAL MCP: My Custom Picks MCP server in PolicyLayer and add a rule for recommend_tracks: 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 TIDAL MCP: My Custom Picks. Nothing to install.
recommend_tracks 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 recommend_tracks 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 recommend_tracks. 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.
recommend_tracks is provided by the TIDAL MCP: My Custom Picks MCP server (mikeysrecipes/tidal-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 →