query_audio
AI agents call query_audio to retrieve information from Perception-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries audio files for information extraction via multimodal models. It retrieves data and returns analysis results without creating, modifying, deleting, or executing external operations. The empty tool description slightly reduces confidence, but the server-level context and sibling tool patterns (query_image, query_video) clearly position this as a read operation.
From the tool's definition Tool name 'query_audio' combined with server description stating 'Enables asking questions about image, audio, or video files' indicates retrieval and analysis of audio data with no modification or side effects.
Attacks that exploit this kind of access
query_audio. It is categorised as a Read tool in the Perception-MCP MCP Server, which means it retrieves data without modifying state.
Register the Perception- MCP server in PolicyLayer and add a rule for query_audio: 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 Perception-MCP. Nothing to install.
query_audio 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 query_audio 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 query_audio. 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.
query_audio is provided by the Perception- MCP server (lintyourcode/perception-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 →