Skip to main content
Glama

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

src/jaz_cloud/

The server: pipeline, API keys, jobs, signed download links

plugins/jaz-cloud/

Claude Code plugin customers install: skill + .mcp.json pointing at your server

skills/jaz/

The same skill on its own, for skills directories

.claude-plugin/marketplace.json

Lets customers run claude plugin marketplace add lnc2131/jaz-cloud

Dockerfile

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-cloud

Claude 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

parse_video(url)

Starts (or reuses) a job and waits up to 25s. Returns the extract, or a job_id if it's still processing.

get_result(job_id)

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/mcp

Try 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 -q

Connect 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) and video (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

JAZ_DATA_DIR

./data

SQLite DB, media, secret key

JAZ_HOST / JAZ_PORT

127.0.0.1 / 8765

JAZ_PUBLIC_BASE_URL

http://127.0.0.1:<port>

Used in download links and allowed Host headers

JAZ_WHISPER_MODEL

large-v3-turbo

Any faster-whisper model name

JAZ_WHISPER_DEVICE

mps on Apple Silicon, else auto

cuda on a GPU server

JAZ_WORKERS

2

Parallel jobs

JAZ_MAX_DURATION_S

3600

Longer videos are refused

JAZ_DAILY_LIMIT_EXTRACT / _VIDEO

30 / 60

JAZ_COOKIES_FILE

none

Netscape cookies file for platforms that demand a login

JAZ_SECRET

generated

Signs download links

Security

  • /mcp needs Authorization: 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_FILE and/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

  1. Billing: Stripe Checkout + webhook that creates/revokes keys per subscription.

  2. Deploy: Dockerfile is a draft; host on a GPU box (or CPU with JAZ_WHISPER_MODEL=small).

  3. 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…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables 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.
      10
      27 npm
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Transforms social media links (TikTok, Instagram, YouTube) and videos into text context with transcription, OCR, and metadata for AI agents like Claude and Cursor.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Turns 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.
      2
      43 npm
      MIT