Json2Video MCP Server

What is Json2Video MCP Server about?

The server enables programmatic creation of videos using json2video's powerful API. It accepts rich JSON definitions describing scenes, elements (text, image, video, audio, components, subtitles, etc.) and returns a project ID for asynchronous rendering.

How to use Json2Video MCP Server?

Install the package globally with npm install -g @omerrgocmen/json2video-mcp or run it directly via npx.
Set the JSON2VIDEO_API_KEY environment variable (or supply apiKey per request).
Invoke the exposed MCP tools:
- generate_video – send a JSON project definition and receive a project ID.
- get_video_status – poll the status of a rendering job using the project ID.
- create_template, get_template, list_templates – manage reusable video templates.
Integrate these calls into LLM prompts, automation scripts, or any MCP‑compatible workflow.

Key features of Json2Video MCP Server

Asynchronous video rendering with simple status polling.
Support for a wide range of element types (text, image, video, audio, component, HTML, voice, audiogram, subtitles).
Flexible JSON schema allowing custom resolutions, quality settings, and per‑scene variables.
Built‑in template management (create, retrieve, list).
API key authentication via environment variable or request payload.
Comprehensive error handling and logging.

Use cases of Json2Video MCP Server

Automatic generation of marketing videos from AI‑generated scripts.
Dynamic video creation in chatbots or virtual assistants.
Batch rendering of personalized video newsletters.
Template‑driven video production pipelines for content teams.
Integration into CI/CD workflows for generating demo or tutorial videos.

FAQ from the Json2Video MCP Server

Q: Do I need to install Node.js locally? A: Yes, the server runs on Node.js. Use npx for a quick start without a global install.

Q: How do I obtain the JSON2VIDEO_API_KEY? A: Sign up at https://json2video.com and generate an API key from your account dashboard.

Q: What if I get a client closed error? A: Run npm i @omerrgocmen/json2video-mcp to ensure the package is properly installed.

Q: Can I specify a custom resolution? A: Set resolution to custom and provide width and height values in the project JSON.

Q: Is the server compatible with Windows? A: Yes. Use cmd /c "set JSON2VIDEO_API_KEY=your_key && npx -y @omerrgocmen/json2video-mcp".

A Model Context Protocol (MCP) server implementation for programmatically generating videos using the json2video API. This server exposes powerful video generation and status-checking tools for use with LLMs, agents, or any MCP-compatible client.

Features

Generate videos with rich scene and element support (text, image, video, audio, components, subtitles, etc.)
Asynchronous video rendering with status polling
Flexible, extensible JSON schema for video projects
Designed for easy integration with LLMs, automation agents, and MCP-compatible tools
API key authentication (env or per-request)
Comprehensive error handling and logging

Installation

Running with npx

env JSON2VIDEO_API_KEY=your_api_key_here npx -y @omerrgocmen/json2video-mcp

Manual Installation

npm install -g @omerrgocmen/json2video-mcp

Windows Users

If you are on Windows and encounter issues, try:

cmd /c "set JSON2VIDEO_API_KEY=your_api_key_here && npx -y @omerrgocmen/json2video-mcp"

Running on Cursor

Cursor v0.48.6+

Open Cursor Settings
Go to Features > MCP Servers
Click "+ Add New MCP Server"
Enter the following:
- Name: "json2video-mcp" (or your preferred name)
- Type: "command"
- Command: env JSON2VIDEO_API_KEY=your_api_key_here npx -y @omerrgocmen/json2video-mcp

Cursor v0.48.6+

Open Cursor Settings
Go to Features > MCP Servers
Click "+ Add new global MCP server"

Enter the following code:

{
  "mcpServers": {
    "json2video-mcp": {
      "command": "npx",
      "args": ["-y", "@omerrgocmen/json2video-mcp"],
      "env": {
        "JSON2VIDEO_API_KEY": "your_api_key_here"
      }
    }
  }
}

Replace your_api_key_here with your json2video API key. You can get an API key from json2video.com.

After adding, refresh the MCP server list to see the new tools. Your agent or LLM will automatically use json2video MCP when appropriate, or you can explicitly request it by describing your video generation needs.

MCP Integration Example

Add this to your mcp.json or similar config:

{
  "mcpServers": {
    "json2video-mcp": {
      "command": "npx",
      "args": ["-y", "@omerrgocmen/json2video-mcp"],
      "env": {
        "JSON2VIDEO_API_KEY": "your_api_key_here"
      }
    }
  }
}

Replace your_api_key_here with your actual json2video API key.
This configuration allows your agent or LLM to start and communicate with the json2video MCP server automatically.
The server will expose the generate_video and get_video_status tools for use in your workflows.

Configuration

Environment Variables

JSON2VIDEO_API_KEY (required): Your json2video API key. Can be set as an environment variable or provided per request.

Note: If you encounter a client closed error, run the following command in your terminal:
npm i @omerrgocmen/json2video-mcp

Usage

Available Tools

1. Generate Video (`generate_video`)

Create a customizable video project with scenes and elements.

Description: Creates a video project using the json2video API. Each project can contain multiple scenes, and each scene can contain various elements such as text, images, video, audio, components, HTML, voice, audiogram, and subtitles. Video generation is asynchronous; use the returned project ID to check status. See https://json2video.com/docs/api/ for full schema and more examples.

Input Schema:

{
  "id": "string (optional, unique identifier for the movie)",
  "comment": "string (optional, project description)",
  "cache": true,
  "client_data": {},
  "draft": true,
  "quality": "high", // one of: low, medium, high
  "resolution": "custom", // one of: sd, hd, full-hd, squared, instagram-story, instagram-feed, twitter-landscape, twitter-portrait, custom
  "width": 1920, // required if resolution is custom
  "height": 1080, // required if resolution is custom
  "variables": {},
  "elements": [ /* global elements, see below for examples */ ],
  "scenes": [
    {
      "id": "string (optional, unique scene id)",
      "comment": "string (optional)",
      "background_color": "#000000",
      "cache": true,
      "condition": "string (optional)",
      "duration": -1,
      "variables": {},
      "elements": [ /* see element examples below */ ]
    }
  ],
  "apiKey": "string (optional)"
}

Element Types & Examples:

Text Element:

{
  "type": "text",
  "text": "Hello world",
  "duration": 5,
  "settings": { "font-size": "60px", "color": "#FF0000" }
}

Image Element:

{
  "type": "image",
  "src": "https://images.pexels.com/photos/1105666/pexels-photo-1105666.jpeg",
  "width": 1620,
  "height": 1080,
  "x": 0,
  "y": 0
}

Video Element:

{
  "type": "video",
  "src": "https://example.com/path/to/my/video.mp4",
  "duration": 7.3
}

Component Element:

{
  "type": "component",
  "component": "basic/001",
  "settings": {
    "headline": { "text": "Lorem ipsum", "color": "white" },
    "body": { "text": "Dolor sit amet" }
  }
}

HTML Element:

{
  "type": "html",
  "html": "<h1>Hello world</h1>",
  "width": 800,
  "height": 600
}

Audio Element:

{
  "type": "audio",
  "src": "https://example.com/audio.mp3",
  "duration": 5
}

Voice Element:

{
  "type": "voice",
  "text": "This is a voiceover.",
  "voice": "en-US-Wavenet-D"
}

Audiogram Element:

{
  "type": "audiogram",
  "color": "#00FF00",
  "amplitude": 5
}

Subtitles Element:

{
  "type": "subtitles",
  "captions": "1\n00:00:00,000 --> 00:00:02,000\nHello world!"
}

Example Input:

{
  "comment": "MyProject",
  "resolution": "full-hd",
  "scenes": [
    {
      "elements": [
        { "type": "video", "src": "https://example.com/path/to/my/video.mp4" },
        { "type": "text", "text": "Hello world", "duration": 5 },
        { "type": "image", "src": "https://images.pexels.com/photos/1105666/pexels-photo-1105666.jpeg", "width": 1620, "height": 1080, "x": 0, "y": 0 },
        { "type": "component", "component": "basic/001", "settings": { "headline": { "text": "Lorem ipsum" } } },
        { "type": "html", "html": "<h1>Hello world</h1>", "width": 800, "height": 600 },
        { "type": "audio", "src": "https://example.com/audio.mp3", "duration": 5 },
        { "type": "voice", "text": "This is a voiceover.", "voice": "en-US-Wavenet-D" },
        { "type": "audiogram", "color": "#00FF00", "amplitude": 5 },
        { "type": "subtitles", "captions": "1\n00:00:00,000 --> 00:00:02,000\nHello world!" }
      ]
    }
  ]
}

Notes for Users:

Each element type has its own required and optional properties. See https://json2video.com/docs/api/ for full details.
You can mix and match element types in scenes and globally.
For custom resolutions, set both width and height.
Use the returned project ID to check video status with get_video_status.

Output:

Returns a project ID to be used with get_video_status.

2. Get Video Status (`get_video_status`)

Check the status or retrieve the result of a video generation job.

Description: Retrieves the status or result of a previously started video generation job. Note: Video rendering is asynchronous and may take some time. If the status is not "done", please try again later using the same project ID.

Input Schema:

{
  "project": "string (required)",
  "apiKey": "string (optional)"
}

Example Input:

{
  "project": "q663vmm2"
}

Example Output:

{
  "success": true,
  "movie": {
    "success": true,
    "status": "done",
    "message": "",
    "project": "q663vmm2",
    "url": "https://assets.json2video.com/clients/yourclient/renders/yourvideo.mp4",
    "created_at": "2025-04-27T10:44:18.880Z",
    "ended_at": "2025-04-27T10:44:28.589Z",
    "duration": 11,
    "size": 359630,
    "width": 640,
    "height": 360,
    "rendering_time": 10
  }
}

3. Create Template (`create_template`)

Create a new template in json2video.

Description: Creates a new template with a given name and optional description.

Input Schema:

{
  "name": "string (required, name of the template)",
  "description": "string (optional, description of the template)",
  "apiKey": "string (optional)"
}

Example Input:

{
  "name": "MyTemplate",
  "description": "A reusable video template."
}

Output:

Returns the template ID if successful.

4. Get Template (`get_template`)

Get template details from json2video.

Description: Retrieves details of a template by its name.

Input Schema:

{
  "name": "string (required, name of the template)",
  "apiKey": "string (optional)"
}

Example Input:

{
  "name": "MyTemplate"
}

Output:

{
    "updated_at": "YYYY-MM-DDTHH:MM:SSZ",
    "created_at": "YYYY-MM-DDTHH:MM:SSZ",
    "movie": "{\"id\":\"template1\",\"comment\":\"Example template\",\"resolution\":\"full-hd\",\"quality\":\"high\",\"scenes\":[{\"id\":\"scene1\",\"comment\":\"Scene 1\",\"elements\":[]}],\"elements\":[],\"width\":1920,\"height\":1080}",
    "name": "MyTemplate",
    "id": "MyTemplate_ID"
  }

5. List Templates (`list_templates`)

List all available templates from json2video.

Description: Lists all templates available to the user.

Input Schema:

{
  "apiKey": "string (optional)"
}

Example Input:

{
}

Output:

[
  {
    "updated_at": "YYYY-MM-DDTHH:MM:SSZ",
    "created_at": "YYYY-MM-DDTHH:MM:SSZ",
    "movie": "{\"id\":\"template1\",\"comment\":\"Example template\",\"resolution\":\"full-hd\",\"quality\":\"high\",\"scenes\":[{\"id\":\"scene1\",\"comment\":\"Scene 1\",\"elements\":[]}],\"elements\":[],\"width\":1920,\"height\":1080}",
    "name": "MyTemplate1",
    "id": "TEMPLATE_ID_1"
  },
  {
    "updated_at": "YYYY-MM-DDTHH:MM:SSZ",
    "created_at": "YYYY-MM-DDTHH:MM:SSZ",
    "movie": "{\"id\":\"template2\",\"resolution\":\"instagram-story\",\"quality\":\"medium\",\"scenes\":[{\"id\":\"scene2\",\"comment\":\"Scene 2\",\"elements\":[]}],\"elements\":[],\"comment\":\"Another template\"}",
    "name": "MyTemplate2",
    "id": "TEMPLATE_ID_2"
  }
]

Json2Video MCP Server