Transcribe an audio or video file to text. This tool uses faster-whisper to transcribe speech from audio/video files. Supports various formats including mp3, wav, mp4, etc. The transcription is saved to two files: - {input_name}.transcript.txt: Contains the transcription text (with timestamps/spe...
AI agents call transcribe to retrieve information from Speech MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads an audio/video file and converts speech to text. While it does write output files (transcript and metadata), its primary function is reading/parsing input data. The output files are derivative artifacts of the read operation. The blast radius is low since it only reads an input file and writes benign text output files derived from it.
From the tool's definition Transcribe an audio or video file to text... The transcription is saved to two files
Documented attack patterns abuse exactly the kind of access transcribe gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Speech MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for transcribe:
{
"version": "1",
"default": "deny",
"tools": {
"transcribe": {}
}
}transcribe is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Transcribe an audio or video file to text. This tool uses faster-whisper to transcribe speech from audio/video files. Supports various formats including mp3, wav, mp4, etc. The transcription is saved to two files: - {input_name}.transcript.txt: Contains the transcription text (with timestamps/speakers if requested) - {input_name}.metadata.json: Contains metadata about the transcription process Args: file_path: Path to the audio or video file to transcribe include_timestamps: Whether to include word-level timestamps (default: False) detect_speakers: Whether to attempt speaker detection (default: False) Returns: A message indicating where the transcription was saved. It is categorised as a Read tool in the Speech MCP MCP Server, which means it retrieves data without modifying state.
Register the Speech MCP server in PolicyLayer and add a rule for 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 Speech MCP. Nothing to install.
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 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 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.
transcribe is provided by the Speech MCP server (kvadratni/speech-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Speech MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Speech MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.