AI agents call identify_instruments 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.
This tool retrieves information from audio data (identifies instruments present) without creating, modifying, deleting, or executing anything. It is a semantic analysis operation that produces insights based on existing audio content. No side effects or irreversible changes occur. This fits cleanly into the Read category as a data analysis and retrieval function.
From the tool's definition The tool 'identify_instruments' reads and analyzes audio files to detect and classify instruments and sound sources. The description explicitly states it performs identification/analysis with no mention of modification, deletion, or code execution.
Attacks that exploit this kind of access
Identify instruments and sound sources in an audio file. 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 identify_instruments: 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.
identify_instruments 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 identify_instruments 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 identify_instruments. 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.
identify_instruments 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 →