download_transcription_model
Download an official whisper.cpp GGML model into the CutPilot local cache.
This record as markdown: /tools/cutpilot/download-transcription-model.md
What download_transcription_model does on Cutpilot
AI agents use download_transcription_model to create or update resources in Cutpilot, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cutpilot environment.
Why download_transcription_model is rated Medium
This tool writes a model file to the local filesystem cache. It is not destructive (no deletion), not financial, and not executing code. It creates/adds new data (a downloaded model file) to local storage, making 'Write' the appropriate category. Severity is medium because downloading external files to local cache could introduce unwanted or large files, but it is limited to official whisper.cpp models.
From the tool's definition Download an official whisper.cpp GGML model into the CutPilot local cache
Attacks that exploit this kind of access
The rule that runs download_transcription_model safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cutpilot, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For download_transcription_model, this is the rule to start with:
download_transcription_model stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Cutpilot, apply this rule, and every download_transcription_model call is checked against it from then on.
Questions about download_transcription_model
Download an official whisper.cpp GGML model into the CutPilot local cache. It is categorised as a Write tool in the Cutpilot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cutpilot MCP server in PolicyLayer and add a rule for download_transcription_model: 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 Cutpilot. Nothing to install.
download_transcription_model is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the download_transcription_model 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 download_transcription_model. 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.
download_transcription_model is provided by the Cutpilot MCP server (Hellotravisss/cutpilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cutpilot, and thousands of servers like it.
This server
Across the catalogue