jev-av-analysis-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@jev-av-analysis-mcp Transcribe and analyze this video for sensitivity flags and publish gate"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
jev-av-analysis-mcp
π¨π³ δΈζζζ‘£
Local-first, zero-key structured audio/video analysis: download β transcribe β decide in one pipeline. Transcription runs on your own machine with yt-dlp + whisper.cpp; analysis uses TypeSafe Jev (System One decision model) to emit structured labels, not prose.
An MCP server that turns any video/audio into "transcript + structured analysis": topic tags, sentiment tone, sensitivity flags (profanity / violence / medical advice / financial advice / politics / copyrighted music / harassment), and a publish gate (publish / review / block). Built for podcasters, video creators, YouTubers β anyone who wants an agent to auto-tag and screen their content.
npm install && npm run build
node dist/index.js doctor # print transcription deps + Jev mode diagnosticsConnect node dist/index.js in your MCP client and use the four tools below.
The four tools
Tool | Purpose |
| URL or local file β transcript (URL via yt-dlp, local/downloaded via whisper.cpp) |
| Use yt-dlp to pull the best audio track of a video/audio to local; returns path + title + duration |
| Local audio/video file β transcript |
| Transcript β Jev structured analysis (see below) |
analyze_transcript takes a piece of text (usually from the three transcription tools above) and returns:
{
"topics": { "tech": 0.9, "business": 0.1, "education": 0.3, "...": 0.0 },
"dominant_topics": ["tech"],
"sentiment": { "score": 3, "label": "positive", "confidence": 0.8, "probabilities": {"0":0,"1":0,"2":0.1,"3":0.8,"4":0.1} },
"sensitivity": { "profanity": 0.1, "violence": 0.0, "medical_advice": 0.2, "financial_advice": 0.9, "...": 0.0 },
"flagged_sensitivity": ["financial_advice"],
"has_key_claims": 0.8,
"has_engagement_hook": 0.4,
"publish_gate": "review",
"confidence": 0.8,
"mocked": false
}Fields
Field | Meaning |
| Membership probabilities over 8 default topics (>0.5 β dominant); override via |
| 5-level ordinal: very_negative β very_positive, with distribution and confidence |
| Probabilities over 7 sensitivity classes; >0.7 β flagged |
| Whether it contains factual claims that need verification (noul probability) |
| Whether the opening has a strong hook (good for short-form clips) |
|
|
| Calibrated confidence of the sentiment dimension |
publish_gate gate logic
publish: no sensitivity class > 0.7review: a sensitivity class in 0.7β0.9 β human review before publishingblock: any sensitivity class > 0.9 β high risk, block
β οΈ Capability boundary (important): Jev is a decision model β it labels / scores, it does not write section headings or summaries. Do chapter segmentation and summarization yourself based on the transcript
segments(or plug in a separate generative model). Before any publishing action, checkpublish_gate+confidencefirst β do not auto-publish just because one probability is high.
Related MCP server: VideoContext MCP
Zero-key / local-first
Transcription layer:
MEDIA_MCP_MOCK=1β skip yt-dlp/whisper and return an offline stub (zero-config for CI/demos). Real mode requiresyt-dlpand a compiledwhisper.cppon your machine, plusWHISPER_MODEL_PATHconfigured.Decision layer: no
TYPESAFE_API_KEYβ automatic Jev mock mode (deterministic offline stub); set it β call the real API.
Environment variables
Variable | Default | Description |
| β | Required for real Jev calls; blank falls back to mock |
|
|
|
|
|
|
|
| Binary paths |
| β | Absolute path to the |
|
| Model name hint |
|
| Transcription timeout |
Install engines locally (real transcription)
pip install yt-dlp
git clone https://github.com/ggerganov/whisper.cpp && cd whisper.cpp && make
# download a small model, e.g.:
bash ./models/download-ggml-model.sh base.en
export WHISPER_MODEL_PATH="$PWD/models/ggml-base.en.bin"Extremely low cost
Transcription runs on your own machine (CPU/GPU, zero call fees); decisions are a single Jev call, tens of thousands of tokens per call. There's no token-usage chart because it's already cheap β think of it as "one cheap gate in your content pipeline".
Tests
npm test # smoke + MCP protocol handshake (dual mock mode, no key needed)License
MIT
Available Tools
4 toolsanalyze_transcriptA
Run a transcript through Jev (System One decision model) for structured analysis: topic membership, sentiment, sensitivity flags (profanity/violence/medical-advice/financial-advice/β¦), and a publish gate (publish / review / block). The agent gets typed labels, not prose. Always check publish_gate + confidence before publishing.
Inputs: transcript (required), categories.
fetch_mediaA
Download the best audio from a video/audio URL to a local file using yt-dlp. Returns the local path plus title and duration. No API key required.
Inputs: url (required), format.
transcribe_fileC
Transcribe a local audio/video file with whisper.cpp. Returns the transcript text and optional segments.
Inputs: path (required), model, language, translate, +1 more.
transcribe_mediaA
Turn any video/audio URL or local file into a transcript, locally and key-free. URLs are fetched with yt-dlp; local files and fetched audio are transcribed with whisper.cpp. Returns the full transcript text plus optional [start --> end] segments.
Inputs: url_or_path (required), model, language, translate, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 4 tools
transcribe_media and transcribe_file overlap for local files, and transcribe_media already handles URL fetching that fetch_media also provides. However, the descriptions make each tool's primary role fairly clear: fetch_media is download-only, transcribe_file is local-only, and transcribe_media is the all-in-one path.
All tool names follow a consistent verb_noun snake_case pattern: transcribe_media, fetch_media, transcribe_file, analyze_transcript. The naming is predictable and easy to navigate.
Four tools is a reasonable size for this audio/video analysis pipeline. The count is only slightly higher than necessary because transcribe_file is mostly redundant with transcribe_media, but it is not bloated.
The server covers the full workflow: fetch media, transcribe it, and analyze the transcript with the Jev model. There are no obvious missing operations for the stated AV-analysis purpose.
Related MCP Connectors
Transcribe, subtitle, dub and lip-sync media; create speech, voices, images and thumbnails.
Transcribe audio and video into speaker-labelled transcripts, subtitles, clips, and cited Q&A.
Transform video, audio and images, and generate media from prompts. FFmpeg, captions, models.
TikTok transcripts, comment sentiment by moment, AI breakdowns and director-level shot analysis.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceDownloads and analyzes videos from platforms like Instagram, YouTube, and TikTok locally, returning keyframes and optional transcripts.MIT
- AlicenseNot gradedqualityCmaintenanceTurns a YouTube video or allowlisted local video into a timestamped transcript, chronological timeline, and retrievable image resources for transparent media preprocessing.1MIT
- AlicenseAqualityCmaintenanceEnables local video inspection and offline transcription with timestamped JSON and Markdown output, enforced filesystem boundaries, and reproducible content-addressed caching.2MIT
- AlicenseNot gradedqualityBmaintenanceProvides local, offline transcription, keyframe extraction, OCR, and pre-publish review of audio, video, and image files, enabling AI agents to see and hear media without cloud or API keys.59 npmApache 2.0