Vedit-MCP

Vedit-MCP provides a dedicated MCP server for video editing tasks. You can issue straightforward editing requests, and the server uses ffmpeg under the hood to produce the edited video. This makes common video edits fast and repeatable via an MCP client.

How to use

To run the Vedit-MCP server locally, start it as a stdio MCP endpoint using Python. You supply the knowledge base directory with the --kb_dir flag, and the server will expose an editing capability you can invoke from your MCP client. You can also integrate this server with your project via the cline-based configuration for streamlined startup.

Practical usage pattern:

• Prepare your knowledge base directory with the required raw video assets.
• Start the MCP server using the standard command and point it to your kb directory.
• From your MCP client, send editing requests (e.g., trim, merge, or effect operations) and receive the processed video as output.

How to install

Prerequisites you need before starting:

• Python installed on your system
• ffmpeg installed and accessible from your PATH
• A client or workflow to send MCP requests to the server (optional during initial testing)

Step-by-step setup commands

• Acquire the server source (clone or download the package)
• Ensure Python environment is ready
• Install dependencies
• Prepare ffmpeg on your system
• Configure and run the server using the standard MCP entry point

# Dependency installation
# It is recommended to use uv for installation
cd vedit-mcp
uv pip install -r requirements.txt

# Alternative: install directly with pip
pip install -r requirements.txt

# Install ffmpeg
# Mac
brew install ffmpeg
# Ubuntu
sudo apt update
sudo apt install ffmpeg

# Start the server via the cline configuration (described below)
# Example: ensure your kb_dir path is ready, then start with the stdio command shown in the config snippet

Additional sections

Configuration and starting details are provided for a stdio MCP setup. The runtime entry point uses a Python script named vedit_mcp.py and a knowledge base directory supplied via --kb_dir.

Security and secrets: if you leverage external APIs during development (for example, to augment capabilities), handle API keys and tokens securely. Do not hard-code secrets in scripts or configuration files. Use environment variables and secret management practices in your deployment.

MCP configuration for stdio startup

{
  "mcpServers": {
    "vedit-mcp": {
      "command": "python",
      "args": [
        "vedit_mcp.py",
        "--kb_dir",
        "your-kb-dir-here"
      ]
    }
  }
}

Environment variables

Set your API key if you rely on external services during development. For example, to configure OpenAI/Volcano Ark Platform access in your environment, export the API key before starting the server.

export OPENAI_API_KEY="your-api-key"

Notes

If you plan to extend functionality or integrate with other MCP components, you can add vedit_mcp.py to your project as a modular entry point for secondary development.