Skip to main content
Glama
omergocmen

json2video MCP Server

by omergocmen
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Remote

json2video MCP Server

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

Related MCP server: Sisif AI MCP Server

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+

  1. Open Cursor Settings

  2. Go to Features > MCP Servers

  3. Click "+ Add New MCP Server"

  4. 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+

  1. Open Cursor Settings

  2. Go to Features > MCP Servers

  3. Click "+ Add new global MCP server"

  4. 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"
  }
]

Available Tools

5 tools
create_templateC

Create a new template in json2video

ParametersJSON Schema
NameRequiredDescriptionDefault
apiKeyNojson2video API key (optional, can also be set as environment variable JSON2VIDEO_API_KEY)
nameYesName of the template
descriptionNoDescription of the template

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It fails to disclose behavioral traits like idempotency, error handling (e.g., duplicate name), authentication requirements beyond the optional apiKey parameter, or whether the created template is returned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely brief (one sentence), but it lacks structure and does not provide any useful elaboration. It is under-specified rather than concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema and annotations, the description should explain what the tool returns (e.g., created template ID) or side effects. It does not, leaving the agent uninformed about the outcome of the operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (all parameters have descriptions). The description adds no additional information beyond the schema, so it meets the baseline but does not enhance understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Create') and the resource ('template') with scope ('in json2video'), differentiating it from siblings like get_template (retrieve) and list_templates (list).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, such as when to create a new template versus using an existing one. No preconditions or dependencies are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

generate_videoC

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. See https://json2video.com/docs/api/ for full schema.

ParametersJSON Schema
NameRequiredDescriptionDefault
idNoUnique identifier for the movie project. If not provided, a random string will be generated.
commentNoA comment or description for the movie project.
cacheNoUse the cached version of the movie if available. Default: true.
client_dataNoKey-value pairs included in the response and webhooks. Used to pass information to later workflow steps.
draftNoIf true, adds a watermark to the movie. Free plans must set draft to true.
qualityNoQuality of the final rendered movie. Use for speed/quality tradeoff.high
resolutionNoPreset resolution. Use "custom" to set width/height manually.custom
widthNoWidth of the movie (pixels). Only if resolution is "custom". Min: 50, Max: 3840.
heightNoHeight of the movie (pixels). Only if resolution is "custom". Min: 50, Max: 3840.
variablesNoGlobal variables for use in templates/components. Variable names: letters, numbers, underscores.
elementsNoGlobal elements not tied to a specific scene. Each element can be of type video, image, text, html, component, audio, voice, audiogram, subtitles.
scenesYesList of scenes in the video. Each scene contains an array of elements.
apiKeyNojson2video API key (optional, can also be set as environment variable JSON2VIDEO_API_KEY)

TDQS

C2.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations available, the description carries the full burden of disclosing behavioral traits. It does not mention that video generation is asynchronous, that it returns a project ID, that there may be costs or API limits, or that the process may take significant time. The only external reference is a URL for the full schema, but critical behavioral context is missing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence plus a link, which is concise. However, it lacks structure: no bullet points, no clear separation of key points. It is not front-loaded with the most critical information (e.g., the required 'scenes' parameter). It is adequate but not well-optimized for quick scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the tool (13 parameters, deeply nested objects, required scenes) and the absence of an output schema, the description is insufficiently complete. It does not explain the return value, the asynchronous nature, the cost implications, or how to handle the response. The tool relies entirely on external documentation, which is poor practice for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and each parameter has a description, so the baseline is 3. The description adds no additional meaning beyond what the schema already provides. It lists element types but that is also covered in the schema. Thus, it does not improve parameter understanding beyond the structured data.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates a video project using the json2video API and lists the types of elements that can be included (text, images, video, etc.). It effectively communicates the primary purpose. However, it does not differentiate from sibling tools like create_template, which also involves creating something, though the distinction is somewhat implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as create_template or get_video_status. It does not mention prerequisites, context, or exclusions. The agent receives no help in deciding whether to invoke this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_templateB

Get template details from json2video

ParametersJSON Schema
NameRequiredDescriptionDefault
apiKeyNojson2video API key (optional, can also be set as environment variable JSON2VIDEO_API_KEY)
nameYesName of the template to search for

TDQS

B3.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden, but it only indicates a read operation without disclosing permissions, side effects, or error conditions. Adequate for a simple retrieval, but could be more transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no redundancy, efficiently conveys the core purpose without unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with only two parameters and no output schema, but the description does not specify what details are returned, leaving the agent without complete context on the return value.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds no extra meaning beyond the parameter names and their schema descriptions, which are already clear.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Get template details from json2video' clearly states the action (get) and resource (template details), and implicitly distinguishes from sibling tools like list_templates, but no explicit differentiation is provided.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use versus alternatives; the context implies use when you have a template name and need details, but no when-not or exclusions are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_video_statusB

Get the status or result of a generated video

ParametersJSON Schema
NameRequiredDescriptionDefault
apiKeyNojson2video API key (optional, can also be set as environment variable JSON2VIDEO_API_KEY)
projectYesProject ID from video generation

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Lacks details on what 'status or result' entails (e.g., polling behavior, response format, mutability). Insufficient for safe invocation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded, and no fluff. Could be slightly more detailed without harming conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Minimal coverage for a simple tool. Lacks explanation of output format or status values. Adequate for a straightforward status check but incomplete for an agent to interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear parameter descriptions. Description adds no additional semantics beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states verb 'Get' and resource 'status or result of a generated video'. Distinct from siblings which are about template creation/list and video generation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage as a follow-up to generate_video, but no explicit guidance on when to use vs. alternatives or exclusions. No mention of siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_templatesB

List all available templates from json2video

ParametersJSON Schema
NameRequiredDescriptionDefault
apiKeyNojson2video API key (optional, can also be set as environment variable JSON2VIDEO_API_KEY)

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It states a read operation but does not disclose behavior like output format, pagination, authentication requirements (optional apiKey), or any limitations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one concise sentence, front-loaded with key information. It could be slightly more informative without sacrificing conciseness, but currently it is efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple tool (1 optional param, no output schema), the description is adequate but minimal. It does not hint at the return structure, which would be useful since no output schema is provided.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, providing full parameter meaning. The description adds no further semantic value beyond what the schema already includes for the optional apiKey parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (List) and resource (all available templates from json2video). It distinguishes from sibling tools like get_template (single) and create_template (write operation).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or when-not-to-use guidance. However, siblings imply this is for getting an overview vs. specific template retrieval. Lacks exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 5 tool updatesv1.3.1
    • First observedcreate_template
    • First observedgenerate_video
    • First observedget_template
    • First observedget_video_status
    • First observedlist_templates
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: creating templates, generating videos, retrieving template details, checking video status, and listing templates. There is no ambiguity or overlap between them.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case (create_template, generate_video, get_template, get_video_status, list_templates), making them predictable and easy to understand.

Tool Count5/5

5 tools is an appropriate number for a video generation server with template management. It covers the core operations without being overwhelming or insufficient.

Completeness4/5

The tool set covers template creation, retrieval, and listing, as well as video generation and status checking. Minor gaps exist, such as missing update and delete operations for templates, but the primary workflow is well-supported.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/omergocmen/json2video-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server