Post Engineer
Overview
Description from the maker (original English)
Create AI personas, generate short videos and schedule posts to YouTube, Instagram and more.
PopNx MCP’s three pillars
These three are never merged into one score: opinions, measurements and popularity are different things.
- User voiceiNo reviews yetReviews open together with accounts in a later step
- Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
- UsageiEarly↓ 1.8K/wk · ★ –
What you can do with it
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
- Connection: Runs on your computer
- Transport: stdio
- Category: Marketing & social media
- You need to fill in: POST_ENGINEER_API_KEY
Install
Pick the AI app you use, then copy the settings.
Before you install
- Basic checks: 1 of 1 passed
- Runs on your computer with your user’s permissions (files, network, apps).
- You fill in yourself:
POST_ENGINEER_API_KEY,POST_ENGINEER_API_URL
Values marked secret are keys to your account. Never share them or paste them into a chat.
You need
- npmNode.js installed (for the npx command)
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"post-engineer": {
"command": "npx",
"args": [
"-y",
"post-engineer-mcp"
],
"env": {
"POST_ENGINEER_API_KEY": "your-value",
"POST_ENGINEER_API_URL": "your-value"
}
}
}
}Run this in your terminal
claude mcp add post-engineer --env POST_ENGINEER_API_KEY=your-value --env POST_ENGINEER_API_URL=your-value -- npx -y post-engineer-mcpFill in the empty values before running it.
Or copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"post-engineer": {
"command": "npx",
"args": [
"-y",
"post-engineer-mcp"
],
"env": {
"POST_ENGINEER_API_KEY": "your-value",
"POST_ENGINEER_API_URL": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Or copy the settings yourself
Paste into .vscode/mcp.json in your project
{
"servers": {
"post-engineer": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"post-engineer-mcp"
],
"env": {
"POST_ENGINEER_API_KEY": "your-value",
"POST_ENGINEER_API_URL": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
Values you fill in
- API key from https://post-engineer.com/recipes
POST_ENGINEER_API_URLenvOverride the API base URL (staging or self-hosted). Defaults to production.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
What it can do
Runs on your computer; the tool list appears in your AI app after you install it.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 9, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account Ryan-Carloso, which owns the repo
- … Not checked yet
Still maintained
We have not read this repo from GitHub yet
- … Not checked yet
Has a licence
We have not read this repo from GitHub yet
- – Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
- – Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
- … Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints
Compared with others in Marketing & social mediai
- More stars than 0% of the other 3631 servers in this category
- Published to the registry more recently than 99% of the other 3631 servers in this category
- Basic checks equal to or better than 100% of the other 3631 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is Post Engineer safe?
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
You need to fill in: POST_ENGINEER_API_KEY
Does it run on my computer or in the cloud?
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
Is it still maintained?
The GitHub repo last changed –, and the latest version (1.45.0) reached the registry today.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
What can I use instead?
In the same category: MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
Alternatives
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Google Analytics MCP
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
BibiGPT YouTube Video Summarizer
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Post Engineer
🇧🇷🇵🇹 Leia em Português
Create AI video personas that generate and publish short videos on autopilot.
Give a persona a niche and a voice; Post Engineer writes the script, generates the voiceover, assembles the video, and publishes it to your social accounts on a schedule. Manage everything from the web dashboard, drive it programmatically through the API, or let your AI agent run it through the MCP server — all from this one monorepo.
Post Engineer is open source under the Apache License, Version 2.0. Self-host the whole platform on your own VPS following docs/SELF_HOSTING.md, or use the hosted version and buy tokens. Lip sync (LongCat) runs on Modal.com: Modal's Starter plan includes $30/month in compute credits (see modal.com/pricing). We are not Modal: this free-credit offer is theirs and can end at any time. Light self-hosted usage can fit inside the free credits while it lasts — usage beyond that is billed by Modal.
Prefer the hosted version? The same platform runs at
post-engineer.com — you can skip the local
setup and connect the MCP server straight to your account (see
MCP server).
What it does
- AI personas — persistent characters with a voice, face, language, and niche. Optional lip-synced intro clips for a human-like presenter, plus a persona image library for face consistency across videos.
- Automatic video generation — topic in, HD short video out: script (LLM), voiceover (TTS), subtitles, stock footage, and background music, assembled into a finished video.
- Scheduling & publishing — queue posts for YouTube, Instagram, LinkedIn, and Bluesky; track upcoming and past posts with per-account status.
- Dashboard — personas, posts history, connected social accounts, API keys, and token billing in one Next.js app.
- Agent control — an MCP server (
apps/mcp/) exposes the same capabilities to AI agents (Claude, Cursor, Codex, OpenCode): create personas, generate videos, check status, and schedule posts.
Repository layout
This is a pnpm/Nx monorepo — web, engine, and MCP live together:
apps/web/ Next.js 15 dashboard + API routes (TypeScript)
apps/engine/ Python/FastAPI video-generation engine apps/mcp/ MCP server for AI agents (npm package: post-engineer-mcp)
The web app owns authentication, personas, scheduling, OAuth, billing, and the API. It calls the engine over HTTP (authenticated with a shared secret, MONEYPRINT_API_SECRET) for video generation, TTS, and publishing. The MCP server talks to the web API with a user API key. Postgres (via Supabase) is the system of record: personas, schedules, OAuth tokens (encrypted at rest), API keys, and token balances.
Prerequisites
- Node.js 20+ and pnpm 10 (
npm install -g pnpmor via corepack) - Python 3.11–3.12 and uv (
curl -LsSf astral.sh/uv/install.sh | sh) - ffmpeg on
PATH(the engine shells out to it via moviepy) - A Supabase project (hosted at supabase.com, or self-hosted) with a Postgres database
- API keys for the external services you plan to use (see the table below)
Local setup from scratch
1. Install dependencies
git clone https://github.com/Ryan-Carloso/post-engineer.git
cd post-engineer pnpm install
2. Set up Supabase
- Create a project at supabase.com (or point at your self-hosted instance).
- In the Supabase SQL editor, apply the database scripts. The persona image library script lives in this repo:
supabase/migrations/002_persona-images.sql(manual-apply by design).
Need help? If you are setting up a fresh project and need the current
schema snapshot, reach out:
Email: madebyryandev@gmail.com ·
WhatsApp: +351 962 248 268
3. Create the three env files (never commit these)
There are exactly three env files by design — copy each from its example and fill in your own values:
cp apps/web/.env.example apps/web/.env
cp apps/engine/.env.example apps/engine/.env cp apps/engine/config.example.toml apps/engine/config.toml
| File | Purpose | Key variables |
|---|---|---|
apps/web/.env | Web app + API routes | NEXT_PUBLIC_SUPABASE_URL, NEXT_PUBLIC_SUPABASE_ANON_KEY, SUPABASE_SERVICE_ROLE_KEY (server-only), TOKEN_ENCRYPTION_KEY (generate: openssl rand -base64 32), MONEYPRINT_API_SECRET, MONEYPRINT_API_URL, OAuth client ids/secrets + redirect URIs, Stripe keys, MCP_OAUTH_PRIVATE_KEY_PEM |
apps/engine/.env | Engine runtime | MONEYPRINT_API_SECRET (must be identical to the web value), SUPABASE_URL + SUPABASE_SERVICE_ROLE_KEY (for the in-process fill scheduler), mandatory R2_ACCOUNT_ID + R2_ACCESS_KEY_ID + R2_SECRET_ACCESS_KEY (final-video archive), optional DISCORD_WEBHOOK_URL, optional POSTHOG_API_KEY (error tracking, analytics funnel, AI observability traces) |
apps/engine/config.toml | Engine behavior config | LLM/TTS/stock-footage provider keys (OpenAI-compatible, Pexels, Pixabay, …), listen_port (default 8080) |
The app fails fast on missing variables (no silent fallbacks) — see apps/web/.env.example for the full documented list.
4. Register OAuth apps (for social publishing)
To connect YouTube, Instagram, or LinkedIn accounts you need OAuth apps whose redirect URIs exactly match the values in apps/web/.env:
- Google / YouTube — Google Cloud Console: create an OAuth 2.0 Client ID, add the authorized redirect URIs from
GOOGLE_REDIRECT_URI/GOOGLE_REDIRECT_URI_LOCAL, and fill inGOOGLE_CLIENT_ID/GOOGLE_CLIENT_SECRET. - Instagram — Meta for Developers: a Business app with the Instagram product (
instagram_business_basicandinstagram_business_content_publishpermissions); setINSTAGRAM_CLIENT_ID/INSTAGRAM_CLIENT_SECRETand registerINSTAGRAM_REDIRECT_URI. - LinkedIn — LinkedIn Developers: create an app, register
LINKEDIN_REDIRECT_URI, and setLINKEDIN_CLIENT_ID/LINKEDIN_CLIENT_SECRET. - Threads — the same Meta app as Instagram (Threads API). Add the Threads product (
threads_basic,threads_content_publishandthreads_manage_insightspermissions) and registerTHREADS_REDIRECT_URI. Threads OAuth usesINSTAGRAM_CLIENT_ID/INSTAGRAM_CLIENT_SECRET. - Bluesky uses an app password entered in the dashboard (encrypted at rest) — no OAuth app registration needed.
5. Stripe setup (token billing)
- Create a Stripe account and get the secret + publishable keys (
STRIPE_SECRET_KEY,NEXT_PUBLIC_STRIPE_PUBLISHABLE_KEY). - Create the token-pack products and put the price IDs in
STRIPE_PRICE_PACK_10/_50/_100. - Add a webhook endpoint pointing at
/api/billing/webhookand store the signing secret inSTRIPE_WEBHOOK_SECRET. The webhook handler verifies the signature and is idempotent.
6. Generate the self-managed secrets
These are yours to create — nothing to register:
# Web <-> engine shared secret (identical in both .env files)
openssl rand -hex 32
OAuth token encryption key (AES-256-GCM)
openssl rand -base64 32
MCP OAuth signing key (PEM, \n-escaped into MCP_OAUTH_PRIVATE_KEY_PEM)
openssl ecparam -genkey -name prime256v1 -noout | openssl pkcs8 -topk8 -nocrypt
Running
pnpm dev:web # dashboard at http://localhost:3434
pnpm dev:engine # video engine API at http://127.0.0.1:8080 (see /docs there)
Useful commands (all verified against package.json / project.json):
pnpm test # all tests (web + engine + MCP, via Nx)
pnpm lint # ESLint (web + MCP) + ruff (engine) pnpm typecheck # tsc --noEmit (web + MCP) + engine checks pnpm build # production build of the web app pnpm graph # Nx project graph
Per-app details: apps/web/README.md, apps/engine/README.md, apps/mcp/README.md.
MCP server
The MCP server (apps/mcp/, npm package post-engineer-mcp) lets AI agents create personas, generate videos, check generation status, and schedule posts on your account. You don't need to clone this repo to use it against the hosted platform:
{
"mcpServers": { "post-engineer": { "type": "local", "command": ["npx", "-y", "post-engineer-mcp@latest"], "environment": { "POST_ENGINEER_API_KEY": " " } } } }
Generate at post-engineer.com/recipes. The @latest tag matters: npx reuses its cached copy without checking for updates. To point the server at your own self-hosted instance instead, set POST_ENGINEER_API_URL (see apps/mcp/README.md for the full tool list, OpenCode timeout tips, and local development).
External services you must key yourself
| Service | Required? | What for | Where to get it |
|---|---|---|---|
| Supabase | Yes | Postgres, auth, storage | supabase.com or self-hosted |
| Google OAuth app | For YouTube publishing | OAuth client id/secret | Google Cloud Console |
| Instagram (Meta) app | For Instagram publishing | OAuth client id/secret | developers.facebook.com |
| LinkedIn app | For LinkedIn publishing | OAuth client id/secret | developer.linkedin.com |
| Stripe | For token billing | Secret/publishable keys, price IDs, webhook secret | stripe.com |
| LLM provider key or Ollama | For script generation | OpenAI-compatible key, or run Ollama locally | Your provider / ollama.com |
| Pexels / Pixabay / Coverr / TwelveLabs | For stock footage | API keys | Respective developer portals |
MONEYPRINT_API_SECRET | Yes | Web ↔ engine auth | Generate yourself (openssl rand -hex 32) |
TOKEN_ENCRYPTION_KEY | Yes | Encrypts OAuth tokens at rest | Generate yourself (openssl rand -base64 32) |
MCP_OAUTH_PRIVATE_KEY_PEM | For MCP server OAuth | Signs MCP tokens | Generate yourself (EC key, see above) |
| PostHog | Optional | Error tracking + product analytics | NEXT_PUBLIC_POSTHOG_KEY (browser), POSTHOG_API_KEY (server), NEXT_PUBLIC_POSTHOG_HOST — see apps/web/.env.example |
| Discord webhook | Optional | Fill-schedule notifications | Discord channel settings |
ZAI_API_KEY | CI only | AI code-review workflow | Not a runtime dependency |
Support & Contact
Questions, get in touch:
- Email: madebyryandev@gmail.com
- WhatsApp: +351 962 248 268
License
Licensed under the Apache License, Version 2.0 — see CONTRIBUTING.md and SECURITY.md.
Credits
Video engine derived from MoneyPrinterTurbo (MIT © 2024 Harry), extended with persona lip-sync, background-music catalog, batch queue, scheduling, and publishing.