zyng-mcp 0.4.0

Zyng MCP client — record your running app with an agent, publish a managed narrated pitch.

zyng-mcp

Record a running app with your coding agent, get back a managed, narrated pitch video — without ever recording it yourself.

Point your agent (Claude Desktop, Claude Code, or any MCP client) at your localhost app. It authors the steps from the source it just wrote; this server drives the app headless with Playwright, screen-records each feature keyless and free, then publishes the clips + your narration context to hosted Zyng (https://app.zyng.work), which stitches and narrates the pitch server-side on your credits and hands back an MP4. No TTS key ever leaves your machine — the data→video engine stays managed.

Tools

tool	what it does	needs
account	your Zyng credit balance (the "do I have credits?" check)	API token
capture_clips	drive a running app headless, screen-record a feature into a raw clip + timeline	Chromium, no key
publish	upload clips + a composition spec → a managed narrated stitch, downloaded as MP4	API token, spends credits

Install

pipx install zyng-mcp            # or: pip install ./zyng_mcp-0.1.0-py3-none-any.whl
python -m playwright install chromium   # one-time browser download (~150MB)

capture_clips needs Chromium; publish does not (the render happens on Zyng). No ffmpeg required.

Get an API token

1. Sign in at https://app.zyng.work (Google).
2. Avatar menu → API tokens → Mint, and copy the zyk_… token (shown once).

A fresh account includes free credits; 1 credit = 1 second of finished video.

Recording apps that need a login

Never put a password in a capture spec — it would land in the agent's context, the tool-call logs, and (if typed on screen) the uploaded video. Three on-machine options instead, all resolved locally so the credential never reaches the agent or Zyng:

HTTP Basic Auth (the browser's WWW-Authenticate dialog — e.g. a staging site):

zyng-mcp secret set staging_basic_auth   # hidden prompt; enter:  username:password

Then pass the secret's name to capture (the agent never sees the value):

{ "do": "capture_clips", "http_auth": "staging_basic_auth" }

Playwright answers the challenge at the network layer — no dialog, nothing on screen, authenticated:true.

Preferred — a saved session (nothing is typed or recorded):

zyng-mcp login http://localhost:3000   # opens a browser; log in by hand, press Enter to save

This writes the authenticated session to ~/.zyng/state/<host>.json (chmod 600). capture_clips auto-detects it for that host, so recordings start already signed in — the result shows "authenticated": true. No login step, no password on screen.

If you must demonstrate the login itself — a named secret (the agent only sees the name):

zyng-mcp secret set acme_password      # hidden prompt; stored in the OS keychain or a chmod-600 file

Then a step references it by name (never the value):

{ "do": "fill", "selector": "#password", "secret": "acme_password" }

The value is resolved at capture time and never enters the spec, the tool call, a log, or the result. Keychain storage needs pipx install "zyng-mcp[keychain]"; otherwise it falls back to ~/.zyng/secrets.json (chmod 600). You can also pass a secret as an env var, e.g. ZYNG_SECRET_ACME_PASSWORD.

Anything visible on screen during capture ends up in the uploaded MP4 — prefer the saved session for anything sensitive, and use a throwaway/test account where you can.

Register with your agent

Add to claude_desktop_config.json (Claude Desktop) or .mcp.json (Claude Code):

{
  "mcpServers": {
    "zyng": {
      "command": "zyng-mcp",
      "env": {
        "ZYNG_API_KEY": "zyk_your_token_here",
        "ZYNG_BASE_URL": "https://app.zyng.work"
      }
    }
  }
}

(If you installed with pipx, zyng-mcp is on your PATH. With a venv, use the absolute path to the zyng-mcp script, or command: "python", args: ["-m", "zyng_mcp.server"].)

Use it

Tell your agent something like:

My app is running at http://localhost:3000. Record the sign-in and the dashboard, then publish a 30-second pitch. Say "this is the fastest way to onboard" over the dashboard.

The agent will, in order: check account for credits, call capture_clips once per feature (authoring the Playwright selectors from your source), assemble a publish spec (title card + clip segments with your narration), and call publish — blocking until Zyng returns the finished MP4 and the share link.

Spec shapes (the agent fills these)

capture_clips spec:

{ "url": "http://localhost:3000", "title": "Dashboard", "aspect": "16:9",
  "steps": [
    { "do": "wait",  "ms": 1000, "say": "Here's the dashboard." },
    { "do": "click", "selector": "text=New report", "say": "One click to a new report." }
  ] }

publish spec (clip files matched by basename to the captured clips you pass in clips):

{ "title": "My app", "theme": "dawn", "voice": "narrator", "aspect": "16:9",
  "segments": [
    { "card": { "layout": "title", "heading": "My app", "narration": "A quick tour." } },
    { "clip": { "file": "dashboard.webm", "audio": "narrate", "say": "This is the dashboard." } }
  ] }

Notes

• Credits + voice are managed. You never ship an ElevenLabs/OpenAI key; Zyng renders with its own voice and charges your balance (gate-at-zero with a clear error).
• Selectors come from your source, not pixel-guessing — Zyng executes the steps your agent authors, so a recording is deterministic and re-runnable. A bad selector returns a clean error naming the step.
• Set ZYNG_BASE_URL to a different host to target a self-hosted or staging studio.