AI agents call get_user_spotify to retrieve information from Lanyard without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves real-time Spotify activity data for a Discord user through the Lanyard API. It is purely informational—it queries and returns data without creating, modifying, deleting, or executing anything. The data retrieved is non-sensitive public presence information (what a user is currently listening to).
From the tool's definition Tool description explicitly states 'Get Spotify listening information' which is a retrieval operation. The word 'Get' indicates data querying with no modifications, deletions, or code execution.
Attacks that exploit this kind of access
Get Spotify listening information for a Discord user via Lanyard - provide Discord user ID. It is categorised as a Read tool in the Lanyard MCP Server, which means it retrieves data without modifying state.
Register the Lanyard MCP server in PolicyLayer and add a rule for get_user_spotify: 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 Lanyard. Nothing to install.
get_user_spotify 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_user_spotify 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_user_spotify. 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_user_spotify is provided by the Lanyard MCP server (nntin/lanyard-mcp-server). 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 →