AI agents call audio_query 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.
With no description available, I rely on the tool name and sibling context. 'Query' typically retrieves or examines data. All sibling tools are read-only analysis operations. This tool almost certainly queries audio metadata or performs analysis without modification. Confidence is 0.8 (not higher) because the empty description prevents full certainty, but the pattern is clear.
From the tool's definition Tool name 'audio_query' and sibling tools (analyze_audio, analyze_for_songwriting, classify_genre, classify_mood, detect_chords, deep_listen) all perform semantic analysis, classification, and transcription of audio without modifying or deleting data.
Attacks that exploit this kind of access
audio_query. 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 audio_query: 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.
audio_query 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 audio_query 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 audio_query. 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.
audio_query 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 →