DaVinci MCP Professional provides a dedicated MCP server that exposes the full range of DaVinci Resolve functionality to MCP clients, such as Claude Desktop or Cursor. The server is designed with a clean, modern Python architecture using async/await patterns and structured error handling to ensure reliability in production environments. Clients can query and control DaVinci Resolve via MCP messages, enabling remote automation, scripting, and integration with other tools in the editing pipeline. To get started, configure Claude Desktop (or your chosen MCP client) to point at this MCP server using the generated server configuration, then start the server and verify connectivity with the built-in test suite and example MCP requests included with the project.

Prerequisites:

• Python 3.8+ and pip
• Git
• Optional: Claude Desktop (for one-click installation) or your preferred MCP client

Manual installation steps:

1. Clone the repository git clone https://github.com/Positronikal/davinci-mcp-professional.git cd davinci-mcp-professional

2. Create and activate a virtual environment (recommended) python -m venv venv

   On Windows

   venv\Scripts\activate.bat

   On macOS/Linux

   source venv/bin/activate

3. Install dependencies pip install -r requirements.txt

4. Configure Claude Desktop (optional but recommended)

   • Open Claude Desktop and locate the MCP/Server configuration settings
   • Add or update the server entry to point at the MCP server configuration (see USING.md or config examples in the repo)

5. Run the MCP server locally python -m davinci_mcp_professional.server

6. (Optional) One-click installation via Desktop Extension (DXT)

   • Download the latest .dxt from Releases
   • Open Claude Desktop > Settings > Extensions
   • Drag and drop the .dxt file to install
   • Configure optional settings (DaVinci Resolve path, debug mode) and start DaVinci Resolve

7. Verify installation

   • Ensure the server starts without errors and responds to basic MCP requests from Claude Desktop or Cursor

Environment variables:

• CLAUDE_DESKTOP_CONFIG: Path or JSON string for Claude Desktop integration configuration. Replace with your actual config path or inline config as required by your setup.
• DAINVICI_RESOLVE_PATH: Optional path to your DaVinci Resolve installation if the server needs to locate Resolve binaries.
• DEBUG: Enable verbose logging (set to '1' to enable).

Common issues:

• Incorrect Python version: Ensure you are using Python 3.8+. Use python --version to confirm.
• Missing dependencies: Run pip install -r requirements.txt in an active virtual environment.
• Client configuration mismatch: Ensure Claude Desktop or Cursor is pointed to the correct MCP server host/port as configured by your deployment.

Tip: For production deployments, consider running behind a process manager (e.g., systemd, PM2-equivalent) and redirect logs to a file for easier monitoring.