DaVinci MCP Professional v3.0.0
A modern, professional Model Context Protocol server for DaVinci Resolve integration
Loading...
Searching...
No Matches
DaVinci MCP Professional

An enterprise-grade Model Context Protocol (MCP) server that exposes the full DaVinci Resolve scripting API to AI assistants. This project is a hard fork of davinci-resolve-mcp by @samuelgursky, rewritten and maintained independently.

Supported MCP clients: Claude Desktop (primary), Gemini CLI, ChatGPT.


Prerequisites

  • DaVinci Resolve (Free or Studio), installed and licensed
  • Python 3.10 or later
  • uv — fast Python package and virtual environment manager

Installation

From source (recommended)

git clone https://github.com/Positronikal/davinci-mcp-professional.git
cd davinci-mcp-professional
uv venv
uv sync

Standalone Windows executable

Download the pre-built davinci-mcp-server.exe from Releases. No Python installation required.


Configuring Claude Desktop

Locate or create your claude_desktop_config.json file:

  • Windows: APPDATA%\Claude\claude_desktop_config.json
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Add the server entry:

Running from source (Windows):

{
"mcpServers": {
"davinci-resolve": {
"name": "DaVinci MCP Professional",
"command": "C:\\path\\to\\davinci-mcp-professional\\.venv\\Scripts\\python.exe",
"args": ["C:\\path\\to\\davinci-mcp-professional\\mcp_server.py"]
}
}
}

Running from source (macOS):

{
"mcpServers": {
"davinci-resolve": {
"name": "DaVinci MCP Professional",
"command": "/path/to/davinci-mcp-professional/.venv/bin/python",
"args": ["/path/to/davinci-mcp-professional/mcp_server.py"]
}
}
}

Using the standalone Windows executable:

{
"mcpServers": {
"davinci-resolve": {
"name": "DaVinci MCP Professional",
"command": "C:\\path\\to\\davinci-mcp-server\\davinci-mcp-server.exe",
"args": []
}
}
}

Restart Claude Desktop after saving the config.


Other Supported Clients

Gemini CLI and ChatGPT support the MCP standard and can connect to this server using the same mcp_server.py entry point. Their MCP integration is still maturing — consult each client's documentation for the current configuration method.


Basic Usage

  1. Start DaVinci Resolve and wait for it to fully load.
  2. Start the MCP server (Claude Desktop does this automatically when configured).
  3. Ask your AI assistant to interact with Resolve:
What version of DaVinci Resolve is running?
List all projects in the database.
Create a new timeline called "Act 1".
Switch to the Color page.
Import /path/to/clip.mp4 into the media pool.

Further Reading

Document Purpose
USING.md Developer setup, build instructions, contributing
BUGS.md Troubleshooting and bug reporting
CONTRIBUTING.md Contribution guidelines
COPYING.md GPL-3.0 license

For developer setup, build instructions, and contribution guidelines, see USING.md.