Skip to main content
MCP (Model Context Protocol) is a model context protocol launched by Anthropic that allows AI models (such as Claude, GPT, etc.) to call external tools through standardized interfaces. With the Sora MCP Server provided by AceData Cloud, you can directly use OpenAI Sora to generate AI videos in AI clients like Claude Desktop, VS Code, Cursor, etc.

​
Feature Overview

The Sora MCP Server provides the following core functionalities:
  • Text to Video Generation — Generate high-quality videos from text prompts
  • Image to Video Generation — Generate videos based on images
  • Character Consistency Video — Maintain character consistency using reference images
  • Asynchronous Generation — Support for asynchronous task submission and result querying
  • Multiple Screen Orientations — Support for landscape and portrait modes
  • Task Querying — Monitor generation progress and obtain results

​
Prerequisites

Before using, you need to obtain an AceData Cloud API Token:
  1. Register or log in to the AceData Cloud platform
  2. Go to the Sora Videos API page
  3. Click “Acquire” to get the API Token (first-time applicants receive free credits)

​
Installation Configuration

pip install mcp-sora

​
Method 2: Source Installation

git clone https://github.com/AceDataCloud/MCPSora.git
cd MCPSora
pip install -e .
Once the installation is complete, you can use the mcp-sora command to start the service.

​
Using in Claude Desktop

Edit the Claude Desktop configuration file:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the following configuration: 
{
  "mcpServers": {
    "sora": {
      "command": "mcp-sora",
      "env": {
        "ACEDATACLOUD_API_TOKEN": "Your API Token"
      }
    }
  }
}
If using uvx (no need to install the package in advance): 
{
  "mcpServers": {
    "sora": {
      "command": "uvx",
      "args": ["mcp-sora"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "Your API Token"
      }
    }
  }
}
After saving the configuration, restart Claude Desktop to use Sora-related tools in the conversation.

​
Using in VS Code / Cursor

Create a .vscode/mcp.json in the project root directory: 
{
  "servers": {
    "sora": {
      "command": "mcp-sora",
      "env": {
        "ACEDATACLOUD_API_TOKEN": "Your API Token"
      }
    }
  }
}
Or use uvx: 
{
  "servers": {
    "sora": {
      "command": "uvx",
      "args": ["mcp-sora"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "Your API Token"
      }
    }
  }
}

​
Available Tools List

Tool NameDescription
sora_generate_videoGenerate video from text prompts
sora_generate_video_from_imageGenerate video based on images
sora_generate_video_with_characterGenerate consistent video using reference character images
sora_generate_video_asyncAsynchronously submit video generation tasks
sora_get_taskQuery the status of a single task
sora_get_tasks_batchBatch query task statuses

​
Usage Examples

After configuration, you can directly call these functions in the AI client using natural language, for example:
  • “Help me generate a video of a cat running on the grass using Sora”
  • “Generate a video from this character photo, maintaining character consistency”
  • “Generate a portrait video with the content of a city sunrise”
  • “Asynchronously generate a video and check the results later”

​
More Information