HyperFrames MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@HyperFrames MCP Servercreate a new project called intro, add a title slide, and render it"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
HyperFrames MCP Server
Remote MCP server for HyperFrames. It exposes HyperFrames project creation, file authoring, linting, validation, composition inspection, rendering, transcription, TTS, catalog access, documentation, and an advanced HyperFrames CLI tool over Streamable HTTP.
Architecture
Claude → Streamable HTTP MCP → this server → HyperFrames CLI → Chromium/FFmpeg → rendered video
This repository does not copy Nate Herk's student kit into your repository. It uses the public HyperFrames npm package directly. The student kit is MIT licensed, while its included AIS brand assets are not licensed for reuse; do not copy those assets into this server.
Related MCP server: Omni-Video Studio MCP
Local run
Requirements: Node.js 22+, FFmpeg, Chromium/Chrome.
npm install
npm startThe MCP endpoint is:
http://localhost:10000/mcp
Health check:
http://localhost:10000/health
Render deployment
This repo includes Dockerfile and render.yaml.
In Render, create a Web Service from this GitHub repository.
Select the Docker runtime (the Blueprint already specifies it).
Deploy the
mainbranch.After deployment, verify
/healthreturns JSON withok: true.Your MCP endpoint is:
https://YOUR-SERVICE.onrender.com/mcp
Render web services must listen on 0.0.0.0 and the PORT environment variable; this server does that by default. The included health check uses /health.
Claude MCP connector
Use the deployed HTTPS endpoint ending in /mcp as a remote Streamable HTTP MCP server.
Example:
https://YOUR-SERVICE.onrender.com/mcpAfter connecting, Claude should discover tools such as:
hyperframes_initproject_write_fileproject_read_fileproject_list_fileshyperframes_linthyperframes_validatehyperframes_compositionshyperframes_renderhyperframes_transcribehyperframes_ttshyperframes_cataloghyperframes_addhyperframes_docshyperframes_doctorhyperframes_cli
Important storage limitation
The default Render filesystem is ephemeral. A project created during one running instance is not a permanent cloud drive and can disappear after instance replacement/redeploy. For serious production use, add persistent storage or object storage for project media and renders.
Security
The service is designed to be easy to connect first. If you expose it publicly, protect the MCP endpoint before using it with untrusted clients. Do not put private media, credentials, or secrets into project files.
HyperFrames
HyperFrames is an HTML-native video framework/CLI. The server uses the installed npm package and its CLI rather than attempting to reimplement the rendering engine.
This server cannot be deployed
Maintenance
Related MCP Connectors
Create and edit images, videos, and audio through Magic Hour's hosted Streamable HTTP MCP server.
Render video and run AI media tasks from a single declarative JSON request.
Remote MCP server exposing SMI Aware tools, resources, and skills over Streamable HTTP.
MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.
Related MCP Servers
- AlicenseCqualityDmaintenanceEnables AI agents to perform headless video editing through 35 tools for project creation, clip manipulation, rendering, quality control, and semantic search, all via JSON-RPC 2.0 over stdio.371MIT
- FlicenseAqualityBmaintenanceEnables AI agents to edit video using text-based proxies, motion graphics via Hyperframes, and advanced FFmpeg rendering, turning any LLM IDE into a professional video editor.4-
- FlicenseNot gradedqualityCmaintenanceWraps HyperFrames CLI as MCP tools, enabling AI agents to create, preview, and render video projects from HTML/CSS/JS, with text-to-speech and transcription capabilities.-
- AlicenseNot gradedqualityAmaintenanceEnables AI clients to create, edit, validate, preview, and render Shotcut projects (saved as MLT XML) without operating the GUI, using structured timeline editing tools and local safety mechanisms.11MIT