Local Whisper
MCPB · LINUX-X64 · 5 COMPONENTS
Private audio and video transcription with Whisper on your own computer, on the GPU or CPU.
Available components
Last scanned (9 hours ago)
Scores higher than 72% of MCPB servers
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
Provenance & Transparency39
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Maintenance history not yet determined.Unverified
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability67
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 658 tokens (~219/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Unverified: 2 categories
Categories scored 0 because we could not verify them: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 38
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed mcpb/https://github.com/OrihuelaConde/local-whisper-mcp/releases/download/v1.1.0/local-whisper-mcp-1.1.0-linux-x64.mcpb
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | mcpb |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
delete_models Delete downloaded models ~95
Deletes downloaded Whisper models to free disk space; status lists them with their sizes. Without model names, it deletes every model, including the voice activity detection model. A deleted model downloads again the next time a transcription needs it. Confirm with the user before calling it.
| Name | Type | Req | Description |
|---|---|---|---|
| models | array|null | – | Models to delete, such as base or large-v3-turbo-q5_0. Omit it to delete all of them. |
No output schema declared.
No examples provided.
status Transcription status ~58
Reports the device that runs Whisper (a GPU or the CPU), the loaded, default, and installed models, model downloads in progress, the inbox folder for audio that isn't on this computer yet, and the allowed folders that transcribe may read audio from.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
transcribe Transcribe audio ~415
Transcribes an audio or video file on this computer with Whisper. The audio never leaves the computer. Reads WAV, Ogg Opus (WhatsApp and Telegram voice notes), and MP3; other formats, such as M4A, need ffmpeg. The file must be in the inbox folder or in one of the allowed folders that the status tool lists. To transcribe a file that isn't on this computer yet, such as a chat attachment, copy it into the inbox: the server deletes files in the inbox after transcribing them, so no copy is left behind.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | Output: txt for plain text, srt for subtitles, or json for segments with start and end times in seconds. |
| hints | array|null | – | Names and terms that are likely to be said in this audio, spelled the way the transcript should write them: people, places, companies, products, or jargon. Whisper uses them as a spelling guide. Pass… |
| language | string|null | – | Language of the audio as a code such as en or es, or auto to detect it. Omit it to use the server default. |
| model | string|null | – | Whisper model, such as large-v3-turbo-q8_0 or base. Omit it to use the server default, which suits almost every case. |
| path | string | yes | Absolute path to the audio file. |
| vad | boolean|null | – | Voice activity detection, which skips silence and noise. Omit it: the server turns it on for clean recordings, where it keeps timestamps exact, and off when background noise could hide quiet speech f… |
No output schema declared.
No examples provided.
How do I install the Local Whisper MCP server?
Local Whisper ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, cba0ea77b8080d8e3fc9de4587255e567b509e236feb3a4d9ea0e94c6dfa5566; the commands to do that are on this page. If it does not match, do not open it.
mcpb · linux-x64
Download bundleCheck the download matches the SHA-256 the MCP registry declares before you open it. If it does not match, do not open the file.
SHA-256
cba0ea77b8080d8e3fc9de4587255e567b509e236feb3a4d9ea0e94c6dfa5566
macOS / Linux
echo "cba0ea77b8080d8e3fc9de4587255e567b509e236feb3a4d9ea0e94c6dfa5566 local-whisper-mcp-1.1.0-linux-x64.mcpb" | shasum -a 256 -c
Windows (PowerShell)
(Get-FileHash -Algorithm SHA256 .\local-whisper-mcp-1.1.0-linux-x64.mcpb).Hash -eq "cba0ea77b8080d8e3fc9de4587255e567b509e236feb3a4d9ea0e94c6dfa5566"
Run it in the folder you saved the bundle to, then open the file with an MCPB-capable host such as Claude Desktop.
What is the Local Whisper MCP server?
Local Whisper is an MCP server listed in the public MCP registry as io.github.OrihuelaConde/local-whisper-mcp. Private audio and video transcription with Whisper on your own computer, on the GPU or CPU. This page covers its MCPB bundle (https://github.com/OrihuelaConde/local-whisper-mcp/releases/download/v1.1.0/local-whisper-mcp-1.1.0-linux-x64.mcpb).
Is the Local Whisper MCP server safe to use?
Local Whisper scores 38 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Local Whisper MCP server expose?
Local Whisper exposes 3 tools: transcribe, delete_models, status. Their descriptions and schemas cost roughly 568 tokens of context every time the server is loaded.
What licence is the Local Whisper MCP server under?
Local Whisper declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.