DaVinci Resolve
DaVinci Resolve MCP Server — 53 tools for AI-powered remote video editing via Claude
What is DaVinci Resolve?
DaVinci Resolve is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to davinci resolve mcp server — 53 tools for ai-powered remote video editing via claude
DaVinci Resolve MCP Server — 53 tools for AI-powered remote video editing via Claude
This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- DaVinci Resolve MCP Server — 53 tools for AI-powered remote
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx resolveConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use DaVinci Resolve
The DaVinci Resolve MCP Server exposes 53 tools that give AI assistants full remote control over DaVinci Resolve's editing, color grading, media management, and rendering capabilities. Built in Python, it connects to Resolve's scripting API over a local socket and lets Claude perform timeline edits, switch color grades, import clips, add markers, export renders, and even describe frame contents using an optional Moondream vision model — all through natural language. It is ideal for editors who want to automate repetitive Resolve tasks or prototype complex edits without touching the GUI.
Prerequisites
- DaVinci Resolve 18 or later installed and running (free or Studio edition)
- Python 3.10+ with pip and venv available
- DaVinci Resolve's scripting API enabled (Preferences > System > General > Enable scripting API)
- Optional: A Moondream API key for vision/frame-description tools
- Claude Desktop or another MCP client configured to run the server
Clone the repository
The server is distributed as source code on GitHub. Clone it to a local directory.
git clone https://github.com/guycochran/resolve-mcp-server.git
cd resolve-mcp-serverCreate a virtual environment and install dependencies
Use a Python virtual environment to isolate the server's dependencies from system Python.
python3 -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txtConfigure environment variables
Copy the example .env file and add your Moondream API key if you want to use vision tools. The server works without this key but vision-based tools will be unavailable.
cp .env.example .env
# Edit .env and set:
# MOONDREAM_API_KEY=your_key_hereAdd the server to Claude Desktop configuration
Edit claude_desktop_config.json to launch the server via the bundled start.sh script. Adjust the path to where you cloned the repository.
{
"mcpServers": {
"resolve": {
"command": "/absolute/path/to/resolve-mcp-server/start.sh"
}
}
}Open DaVinci Resolve and start Claude Desktop
DaVinci Resolve must be open and running before the MCP server attempts to connect. Start Resolve first, then launch Claude Desktop. The server will connect to Resolve's local scripting socket automatically.
Alternatively run in HTTP mode for remote access
For remote or multi-client setups, run the server in HTTP transport mode on a configurable port.
TRANSPORT=http PORT=3001 .venv/bin/python3 src/server.pyDaVinci Resolve Examples
Client configuration
Claude Desktop configuration using the start.sh launcher script from the cloned repository.
{
"mcpServers": {
"resolve": {
"command": "/Users/you/resolve-mcp-server/start.sh"
}
}
}Prompts to try
Use natural language to control DaVinci Resolve editing, color, and rendering tasks.
- "Replace the b-roll clip at 13:22 with the South Pole takeoff shot and preserve the audio"
- "Add a marker at the current playhead position labeled 'review this transition'"
- "Apply the Kodak 2383 LUT to all clips in the current timeline"
- "Export the current timeline to YouTube 1080p HD"
- "What's in this frame? Describe the shot composition and any people visible"
- "Switch to the color page and create a new color version called 'warm grade'"Troubleshooting DaVinci Resolve
Server fails to connect to DaVinci Resolve
Ensure DaVinci Resolve is open before starting the MCP server. Go to Preferences > System > General and confirm 'Enable scripting using local network' is checked. Restart Resolve after changing this setting.
start.sh permission denied error
Make the launch script executable: chmod +x /path/to/resolve-mcp-server/start.sh. Also ensure the .venv directory was created inside the repository root as the script expects it there.
Vision tools return errors or are unavailable
Vision tools require a valid MOONDREAM_API_KEY set in the .env file. Without it the tools will fail. Obtain a key from moondream.ai and add it to .env, then restart the server.
Frequently Asked Questions about DaVinci Resolve
What is DaVinci Resolve?
DaVinci Resolve is a Model Context Protocol (MCP) server that davinci resolve mcp server — 53 tools for ai-powered remote video editing via claude It connects AI assistants to external tools and data sources through a standardized interface.
How do I install DaVinci Resolve?
Follow the installation instructions on the DaVinci Resolve GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with DaVinci Resolve?
DaVinci Resolve works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is DaVinci Resolve free to use?
Yes, DaVinci Resolve is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
DaVinci Resolve Alternatives — Similar Browser Automation Servers
Looking for alternatives to DaVinci Resolve? Here are other popular browser automation servers you can use with Claude, Cursor, and VS Code.
Chrome DevTools MCP
★ 40.6kAI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and suppo
UI TARS Desktop
★ 34.9k📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.
Playwright
★ 32.8kA production-ready browser automation server that enables AI assistants to interact with web pages using tools for navigation, element interaction, and data extraction. It features a built-in Inspector UI and robust crash recovery for reliable automa
Page Agent
★ 18.0kJavaScript in-page GUI agent. Control web interfaces with natural language.
Chrome
★ 11.7kAn extension-based MCP server that enables AI assistants to control your browser, leveraging existing sessions and login states for automation and content analysis. It provides over 20 tools for semantic tab search, interactive element manipulation,
LAMDA
★ 7.8kThe most powerful Android RPA agent framework, next generation mobile automation.
Browse More Browser Automation MCP Servers
Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up DaVinci Resolve in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use DaVinci Resolve?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.