MCP server that inspects a screen recording, returns real visual evidence to ChatGPT, and then uses FFmpeg and ElevenLabs to create a narrated tutorial. ChatGPT performs the visual reasoning and write
View on GitHub ↗TutorialFlow is a Railway-first MCP server that inspects a screen recording, returns real visual evidence to ChatGPT, and then uses FFmpeg and ElevenLabs to create a narrated tutorial. ChatGPT performs the visual reasoning and writes the script. Railway creates a consistent thumbnail from a real frame, and ChatGPT may optionally create a more elaborate image with its native image-generation capability. No OpenAI or other vision API is called by the backend.
This repository is public, but the running service is not a shared hosted product. Each friend or peer should deploy their own Railway service with their own ElevenLabs API key. The checked-in mcp.json contains a placeholder URL so installing a copy cannot silently use the maintainer's Railway service or ElevenLabs credits. The MCP endpoint has no user authentication yet; see Security notes before inviting others to one deployment.
1. Fork TutorialFlowMCP on GitHub into your account. A local Python or FFmpeg installation is not needed for Railway use. 2. In ElevenLabs, create an API key with Voices Read and Text to Speech access. Keep the key secret and set an account or key usage limit you are comfortable with. You need the API key secret, not the key ID. 3. In Railway, create a project, choose Deploy from GitHub repo, and select your fork. The included Dockerfile installs Python and FFmpeg. Railway hosting and ElevenLabs usage may incur charges. 4. In the Railway service's Variables tab, set ELEVENLABSAPIKEY to your secret. Set ARTIFACTSECRET to a long random value and, if desired, PROJECTTTLHOURS=24 (the default). L
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/smshozab--TutorialFlowMCP.html)
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is
zhuyansen/new-term-radarDaily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.
yzg1226/mcd-party-officer🍟 麦当劳门店派对成团调度 Skill — 把派对从「策划」推进到「办得成」：成团概率雷达 / 包场vs拼团 / 择日黄历 / 儿童营养指数 / 招募卡与邀请函
fellowgeek/mcp-memoryAn OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents.
hirotomasato/yowesGenerate realistic teacher documents (ID cards, licenses, letters) for 13 countries via MCP.
hujjun/mcd-saver-strategist麦当劳省钱点餐助手（麦门精算师）｜麦当劳优惠券组合优化 Skill：拉取麦当劳菜单与全部可用优惠券，算出最省的点餐组合，巨无霸套餐 ¥47 → ¥21.9（省 53%）。McDonalds MCP（麦当劳 MCP）coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · 麦当劳程序员创意开发大赛参赛作品
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.