AI agents call classify_genre to retrieve information from Claud-Ear without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads/analyzes an audio file to classify its genre and return results. It does not create, modify, delete, or execute code/commands. No side effects or state changes are implied. This fits the Read category: it retrieves or queries data to produce analytical output.
From the tool's definition Tool performs genre classification on audio files and returns ranked predictions with no modification of data or triggering of external operations. This is purely a retrieval and analysis operation that examines existing audio content.
Attacks that exploit this kind of access
Classify the genre of an audio file. Returns ranked genre predictions. It is categorised as a Read tool in the Claud-Ear MCP Server, which means it retrieves data without modifying state.
Register the Claud-Ear MCP server in PolicyLayer and add a rule for classify_genre: 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 Claud-Ear. Nothing to install.
classify_genre 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 classify_genre 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 classify_genre. 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.
classify_genre is provided by the Claud-Ear MCP server (null-phnix/claud-ear). 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 →