listening_clock
Profile when you listen by UTC hour (24-bucket histogram plus daypart totals, peak hour and quietest hour) from recently-played history (default 150 items); hour buckets come from the UTC clock of played_at, the same frame as the day-scoped metrics, so they agree with them in any host time zone. ...
This record as markdown: /tools/novalux12-spotify-mcp/listening-clock.md
What listening_clock does on Spotify
AI agents use listening_clock to create or update resources in Spotify, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Spotify environment.
Why listening_clock is rated Medium
An AI agent can call listening_clock faster than any human can review: one bad instruction and it creates or modifies resources in Spotify by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs listening_clock safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Spotify, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For listening_clock, this is the rule to start with:
listening_clock stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Spotify, apply this rule, and every listening_clock call is checked against it from then on.
Questions about listening_clock
Profile when you listen by UTC hour (24-bucket histogram plus daypart totals, peak hour and quietest hour) from recently-played history (default 150 items); hour buckets come from the UTC clock of played_at, the same frame as the day-scoped metrics, so they agree with them in any host time zone. quietest_hour is set only when a single hour holds the fewest plays; when several tie, it is null and quietest_tied_hours lists them in ascending order, because a thin history cannot identify a quietest hour. Quota: GET /me/player/recently-played cursor walk. It is categorised as a Write tool in the Spotify MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Spotify MCP server in PolicyLayer and add a rule for listening_clock: 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. Nothing to install.
listening_clock is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the listening_clock 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 listening_clock. 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.
listening_clock is provided by the Spotify MCP server (@novalux12/spotify-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Spotify, and thousands of servers like it.
This server
Across the catalogue