音频转写：支持 wav/mp3/m4a/flac 等格式。使用 Qwen3-ASR (mlx-audio)。
AI agents call audio_transcribe to retrieve information from Local Mmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Audio transcription is fundamentally a read operation—it processes input audio and returns a text representation without side effects, irreversible changes, or code execution. The tool does not create, modify, delete, or execute anything; it merely extracts information from audio data. This is consistent with Read category semantics (retrieves or queries data; no side effects).
From the tool's definition Tool transcribes audio files (wav/mp3/m4a/flac formats) using Qwen3-ASR. The description contains no indication of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
音频转写：支持 wav/mp3/m4a/flac 等格式。使用 Qwen3-ASR (mlx-audio)。. It is categorised as a Read tool in the Local Mmcp MCP Server, which means it retrieves data without modifying state.
Register the Local M MCP server in PolicyLayer and add a rule for audio_transcribe: 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 Local Mmcp. Nothing to install.
audio_transcribe 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_transcribe 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_transcribe. 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_transcribe is provided by the Local M MCP server (rorojiao/local-mmcp). 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 →