Skip to the previous track.
AI agents invoke previous to trigger actions in Spotify MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool controls Spotify playback by navigating to the previous track. It triggers an external operation (changing the currently playing track) rather than simply reading data or writing persistent data. It is reversible (you can go forward again), so it's Execute rather than Destructive. The blast radius is low as it only affects music playback.
From the tool's definition 'Skip to the previous track' triggers an external operation on Spotify playback state
Attacks that exploit this kind of access
Skip to the previous track. It is categorised as a Execute tool in the Spotify MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Spotify MCP Server MCP server in PolicyLayer and add a rule for previous: 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 Spotify MCP Server. Nothing to install.
previous is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the previous 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 previous. 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.
previous is provided by the Spotify MCP Server MCP server (obre10off/spotify-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 →