Jaz Cloud
Processes Facebook links to extract captions, timestamped voiceover transcripts, and on-screen text from videos.
Processes Instagram links to extract video captions, timestamped voiceover transcripts, and deduplicated on-screen text from downloaded media.
Processes Pinterest links to extract available captions, timestamped transcripts, and on-screen text from linked video content.
Processes TikTok links to extract captions, timestamped voiceover transcripts, and on-screen text from videos.
Processes YouTube links, including share-link variants, to return captions, timestamped transcripts, and on-screen text from videos.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Jaz Cloud
Status: personal self-hosting. Right now this runs on my own always-on Mac so I can use Jaz from my phone (SELF-HOST.md). It's also the template for a possible paid, hosted version later: the server, API keys, daily limits and plugin work today; billing and cloud deployment aren't built. For the free version that runs on your own computer, use Jaz.
A hosted MCP server that lets AI agents "watch" video links. Send it an Instagram, TikTok, YouTube, Pinterest, X or Facebook link (or any web page) and it returns the caption, the voiceover transcript with timestamps, and the text shown on screen.
Repo layout
Path | What it is |
| The server: pipeline, API keys, jobs, signed download links |
| Claude Code plugin customers install: skill + |
| The same skill on its own, for skills directories |
| Lets customers run |
| Draft container for deployment (untested) |
Related MCP server: Social → Context
Customer install (once deployed)
claude plugin marketplace add lnc2131/jaz-cloud
claude plugin install jaz-cloud@jaz-cloudClaude Code asks for the API key (jaz_...) during install. Before publishing, replace
https://YOUR-DOMAIN/mcp in plugins/jaz-cloud/.mcp.json with your server's address.
link ─► yt-dlp download ─► ffmpeg ─┬─► faster-whisper ─► transcript
└─► frames every 1.5s ─► RapidOCR ─► on-screen text (deduped)Agents call two MCP tools:
Tool | What it does |
| Starts (or reuses) a job and waits up to 25s. Returns the extract, or a |
| Waits up to 25s more for a job and returns the extract. |
The agent builds recipes, place lists and so on from the extract (see
plugins/jaz-cloud/skills/jaz/SKILL.md), so the server needs no LLM API key.
Run it locally
uv sync
uv run jaz-cloud keys create --label me --plan video # prints the key once
uv run jaz-cloud serve # http://127.0.0.1:8765/mcpTry it without a client:
uv run jaz-cloud extract "https://youtu.be/jNQXAC9IVRw"
uv run python tests/smoke.py <api-key> "https://youtu.be/jNQXAC9IVRw"
uv run pytest -qConnect Claude Code to the local server:
claude mcp add --transport http jaz-cloud http://127.0.0.1:8765/mcp --header "Authorization: Bearer <api-key>"Accounts and limits
API keys are stored as SHA-256 hashes.
keys create | list | revoke <prefix>.Plans:
extract(30 new links/day) andvideo(60/day, plus signed download links for the original files that last 21 days).The same link (any share-link variant for YouTube) on the same UTC day is free for a key that already asked for it, and reuses the finished job across keys.
Failed jobs don't count toward the limit.
Settings (environment variables)
Variable | Default | Notes |
|
| SQLite DB, media, secret key |
|
| |
|
| Used in download links and allowed Host headers |
|
| Any faster-whisper model name |
|
|
|
|
| Parallel jobs |
|
| Longer videos are refused |
|
| |
| none | Netscape cookies file for platforms that demand a login |
| generated | Signs download links |
Security
/mcpneedsAuthorization: Bearer <key>; everything else is public (/healthz, signed/files/...links).Links that resolve to private, loopback or cloud-metadata addresses are refused (SSRF). Known gap: DNS rebinding between the check and the fetch.
Known limits
Platform blocking is the main risk of hosting. Instagram, TikTok and YouTube often block or demand logins from datacenter IPs. Works from a home connection; on a server you'll likely need
JAZ_COOKIES_FILEand/or residential proxies. Check each platform's terms before offering this commercially.Instagram/TikTok photo-only posts depend on yt-dlp support and may fail.
Transcripts and OCR are machine output and can contain mistakes.
No billing yet: keys are created by hand.
Roadmap
Billing: Stripe Checkout + webhook that creates/revokes keys per subscription.
Deploy: Dockerfile is a draft; host on a GPU box (or CPU with
JAZ_WHISPER_MODEL=small).Optional server-side structured extract (recipes, places) with an LLM.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Turn any video or audio link into files, transcripts and metadata, right from your AI agent.
Turn a TikTok/Instagram/YouTube link into text for your AI: metadata, transcript and image OCR.
Transcripts and AI summaries of TikTok, YouTube, Instagram, Facebook and X videos from a link.
Transcripts, summaries, chapters and timestamped search for video links, for AI agents.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI agents to download, transcribe, and read metadata for any video or audio URL - YouTube, TikTok, X, podcasts and 1000+ sites - working from agent sandboxes and servers where direct downloads usually get blocked. $3 free credit, no card.1027 npmMIT
- AlicenseNot gradedqualityDmaintenanceTransforms social media links (TikTok, Instagram, YouTube) and videos into text context with transcription, OCR, and metadata for AI agents like Claude and Cursor.MIT
- AlicenseAqualityCmaintenanceEnables agents to turn public video links into timestamped transcripts, chapters, and clip suggestions for YouTube, Twitch, Kick, and TikTok.3MIT
- AlicenseAqualityCmaintenanceTurns TikTok, Instagram, X/Twitter and Facebook post URLs into video download links plus metadata (title, author, duration, thumbnail), so AI agents can fetch social videos in one tool call.243 npmMIT