io.github.AceDataCloud/mcp-sora

Official

by AceDataCloud · Python

MCP server for OpenAI Sora AI video generation

Generates videos using OpenAI's Sora AI video generation model.

Topics

ai-videomcp-servermodel-context-protocolvideo-generationdeveloper-toolssora-api

README.md15 KBView on GitHub

SoraMCP

A Model Context Protocol (MCP) server for AI video generation using Sora through the AceDataCloud API.

Generate AI videos directly from Claude, VS Code, or any MCP-compatible client.

Features

Text-to-Video - Generate videos from text descriptions
Image-to-Video - Animate images and create videos from reference images
Character Videos - Reuse characters across different scenes
Async Generation - Webhook callbacks for production workflows
Multiple Orientations - Landscape and portrait videos
Task Tracking - Monitor generation progress and retrieve results

Tool Reference

Tool	Description
`sora_generate_video`	Generate an AI video from a text prompt using Sora.
`sora_generate_video_from_image`	Generate an AI video from reference images using Sora (Image-to-Video).
`sora_generate_video_with_character`	Generate an AI video featuring a character from a reference video.
`sora_generate_video_async`	Generate an AI video asynchronously with callback notification.
`sora_generate_video_v2`	Generate an AI video using Sora Version 2 (partner channel).
`sora_generate_video_v2_async`	Generate an AI video asynchronously using Sora Version 2 with callback.
`sora_get_task`	Query the status and result of a video generation task.
`sora_get_tasks_batch`	Query multiple video generation tasks at once.
`sora_list_models`	List all available Sora models and their capabilities.
`sora_list_actions`	List all available Sora API actions and corresponding tools.

Quick Start

1. Get Your API Token

Sign up at AceDataCloud Platform
Go to the API documentation page
Click "Acquire" to get your API token
Copy the token for use below

2. Use the Hosted Server (Recommended)

AceDataCloud hosts a managed MCP server — no local installation required.

Endpoint: https://sora.mcp.acedata.cloud/mcp

All requests require a Bearer token. Use the API token from Step 1.

Claude.ai

Connect directly on Claude.ai with OAuth — no API token needed:

Go to Claude.ai Settings → Integrations → Add More
Enter the server URL: https://sora.mcp.acedata.cloud/mcp
Complete the OAuth login flow
Start using the tools in your conversation

Claude Desktop

Add to your config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

json

{
  "mcpServers": {
    "sora": {
      "type": "streamable-http",
      "url": "https://sora.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Cursor / Windsurf

Add to your MCP config (.cursor/mcp.json or .windsurf/mcp.json):

json

{
  "mcpServers": {
    "sora": {
      "type": "streamable-http",
      "url": "https://sora.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

VS Code (Copilot)

Add to your VS Code MCP config (.vscode/mcp.json):

json

{
  "servers": {
    "sora": {
      "type": "streamable-http",
      "url": "https://sora.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Or install the Ace Data Cloud MCP extension for VS Code, which registers the hosted MCP servers with one-click setup.

JetBrains IDEs

Go to Settings → Tools → AI Assistant → Model Context Protocol (MCP)
Click Add → HTTP
Paste:

json

{
  "mcpServers": {
    "sora": {
      "url": "https://sora.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Claude Code

Claude Code supports MCP servers natively:

bash

claude mcp add sora --transport http https://sora.mcp.acedata.cloud/mcp \
  -h "Authorization: Bearer YOUR_API_TOKEN"

Or add to your project's .mcp.json:

json

{
  "mcpServers": {
    "sora": {
      "type": "streamable-http",
      "url": "https://sora.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Cline

Add to Cline's MCP settings (.cline/mcp_settings.json):

json

{
  "mcpServers": {
    "sora": {
      "type": "streamable-http",
      "url": "https://sora.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Amazon Q Developer

Add to your MCP configuration:

json

{
  "mcpServers": {
    "sora": {
      "type": "streamable-http",
      "url": "https://sora.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Roo Code

Add to Roo Code MCP settings:

json

{
  "mcpServers": {
    "sora": {
      "type": "streamable-http",
      "url": "https://sora.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Continue.dev

Add to .continue/config.yaml:

yaml

mcpServers:
  - name: sora
    type: streamable-http
    url: https://sora.mcp.acedata.cloud/mcp
    headers:
      Authorization: "Bearer YOUR_API_TOKEN"

Zed

Add to Zed's settings (~/.config/zed/settings.json):

json

{
  "language_models": {
    "mcp_servers": {
      "sora": {
        "url": "https://sora.mcp.acedata.cloud/mcp",
        "headers": {
          "Authorization": "Bearer YOUR_API_TOKEN"
        }
      }
    }
  }
}

cURL Test

bash

# Health check (no auth required)
curl https://sora.mcp.acedata.cloud/health

# MCP initialize
curl -X POST https://sora.mcp.acedata.cloud/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'

3. Or Run Locally (Alternative)

If you prefer to run the server on your own machine:

bash

# Install from PyPI
pip install mcp-sora
# or
uvx mcp-sora

# Set your API token
export ACEDATACLOUD_API_TOKEN="your_token_here"

# Run (stdio mode for Claude Desktop / local clients)
mcp-sora

# Run (HTTP mode for remote access)
mcp-sora --transport http --port 8000

Claude Desktop (Local)

json

{
  "mcpServers": {
    "sora": {
      "command": "uvx",
      "args": ["mcp-sora"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your_token_here"
      }
    }
  }
}

Docker (Self-Hosting)

bash

docker pull ghcr.io/acedatacloud/mcp-sora:latest
docker run -p 8000:8000 ghcr.io/acedatacloud/mcp-sora:latest

Clients connect with their own Bearer token — the server extracts the token from each request's Authorization header.

Available Tools

Video Generation

Tool	Description
`sora_generate_video`	Generate video from a text prompt
`sora_generate_video_from_image`	Generate video from reference images
`sora_generate_video_with_character`	Generate video with a character from reference video
`sora_generate_video_async`	Generate video with callback notification

Tasks

Tool	Description
`sora_get_task`	Query a single task status
`sora_get_tasks_batch`	Query multiple tasks at once

Information

Tool	Description
`sora_list_models`	List available Sora models
`sora_list_actions`	List available API actions

Usage Examples

Generate Video from Prompt

code

User: Create a video of a sunset over mountains

Claude: I'll generate a sunset video for you.
[Calls sora_generate_video with prompt="A beautiful sunset over mountains..."]

Generate from Image

code

User: Animate this image of a city skyline

Claude: I'll bring this image to life.
[Calls sora_generate_video_from_image with image_urls and prompt]

Character-based Video

code

User: Use the robot character in a new scene

Claude: I'll create a new scene with the robot character.
[Calls sora_generate_video_with_character with character_url and prompt]

Available Models

Model	Max Duration	Quality	Features
`sora-2`	15 seconds	Good	Standard generation
`sora-2-pro`	25 seconds	Best	Higher quality, longer videos

Video Options

Size:

small - Lower resolution, faster generation
large - Higher resolution (recommended)

Orientation:

landscape - 16:9 (YouTube, presentations)
portrait - 9:16 (TikTok, Instagram Stories)

Duration:

10 seconds - All models
15 seconds - All models
25 seconds - sora-2-pro only

Configuration

Environment Variables

Variable	Description	Default
`ACEDATACLOUD_API_TOKEN`	API token from AceDataCloud	Required
`ACEDATACLOUD_API_BASE_URL`	API base URL	`https://api.acedata.cloud`
`ACEDATACLOUD_OAUTH_CLIENT_ID`	OAuth client ID (hosted mode)	—
`ACEDATACLOUD_PLATFORM_BASE_URL`	Platform base URL	`https://platform.acedata.cloud`
`SORA_DEFAULT_MODEL`	Default model	`sora-2`
`SORA_DEFAULT_SIZE`	Default video size	`large`
`SORA_DEFAULT_DURATION`	Default duration (seconds)	`15`
`SORA_DEFAULT_ORIENTATION`	Default orientation	`landscape`
`SORA_REQUEST_TIMEOUT`	Request timeout (seconds)	`3600`
`LOG_LEVEL`	Logging level	`INFO`

Command Line Options

bash

mcp-sora --help

Options:
  --version          Show version
  --transport        Transport mode: stdio (default) or http
  --port             Port for HTTP transport (default: 8000)

Development

Setup Development Environment

bash

# Clone repository
git clone https://github.com/AceDataCloud/SoraMCP.git
cd SoraMCP

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # or `.venv\Scripts\activate` on Windows

# Install with dev dependencies
pip install -e ".[dev,test]"

Run Tests

bash

# Run unit tests
pytest

# Run with coverage
pytest --cov=core --cov=tools

# Run integration tests (requires API token)
pytest tests/test_integration.py -m integration

Code Quality

bash

# Format code
ruff format .

# Lint code
ruff check .

# Type check
mypy core tools

Build & Publish

bash

# Install build dependencies
pip install -e ".[release]"

# Build package
python -m build

# Upload to PyPI
twine upload dist/*

Project Structure

code

SoraMCP/
├── core/                   # Core modules
│   ├── __init__.py
│   ├── client.py          # HTTP client for Sora API
│   ├── config.py          # Configuration management
│   ├── exceptions.py      # Custom exceptions
│   ├── server.py          # MCP server initialization
│   ├── types.py           # Type definitions
│   └── utils.py           # Utility functions
├── tools/                  # MCP tool definitions
│   ├── __init__.py
│   ├── video_tools.py     # Video generation tools
│   ├── task_tools.py      # Task query tools
│   └── info_tools.py      # Information tools
├── prompts/                # MCP prompt templates
│   └── __init__.py
├── tests/                  # Test suite
│   ├── conftest.py
│   ├── test_client.py
│   ├── test_config.py
│   ├── test_integration.py
│   └── test_utils.py
├── deploy/                 # Deployment configs
│   └── production/
│       ├── deployment.yaml
│       ├── ingress.yaml
│       └── service.yaml
├── .env.example           # Environment template
├── .gitignore
├── CHANGELOG.md
├── Dockerfile             # Docker image for HTTP mode
├── docker-compose.yaml    # Docker Compose config
├── LICENSE
├── main.py                # Entry point
├── pyproject.toml         # Project configuration
└── README.md

API Reference

This server wraps the AceDataCloud Sora API:

Sora Videos API - Video generation
Sora Tasks API - Task queries

Contributing

Contributions are welcome! Please:

Fork the repository
Create a feature branch (git checkout -b feature/amazing)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing)
Open a Pull Request

License

MIT License - see LICENSE for details.

Links

Made with love by AceDataCloud

Install

Configuration

Environment variables

ACEDATACLOUD_API_TOKENrequiredsecret

API token from Ace Data Cloud (https://platform.acedata.cloud)

claude_desktop_config.json

{
  "mcpServers": {
    "mcp-sora": {
      "command": "uvx",
      "args": [
        "mcp-sora"
      ],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "<YOUR_ACEDATACLOUD_API_TOKEN>"
      }
    }
  }
}