This MCP server exposes a DaVinci Resolve integration that enables AI assistants to query and control Resolve via natural language. It bridges the MCP (Model Context Protocol) interface with DaVinci Resolve's scripting environment so tools like Cursor or Claude Desktop can issue commands, retrieve project data, manage timelines, and automate common tasks within Resolve. After starting the server, you can connect your preferred AI client and begin natural language conversations that translate into Resolve actions, such as opening a project, selecting timelines, exporting renders, or applying edits. The server is designed to work with the Cursor and Claude Desktop integrations described in the repository, and it includes configuration templates to tailor client behavior and Resolve paths to your installation.

Prerequisites:

• macOS or Windows with DaVinci Resolve installed
• Python 3.6+ installed
• JavaScript tooling is optional if you plan to use any web-based tooling

Step-by-step installation:

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

2. Create and activate a Python virtual environment:

   macOS/Linux

   python -m venv venv source venv/bin/activate

   Windows

   venv\Scripts\activate

3. Install dependencies from requirements.txt: pip install -r requirements.txt

   Or install the MCP SDK directly if preferred:

   pip install git+https://github.com/modelcontextprotocol/python-sdk.git

4. Set up DaVinci Resolve scripting environment variables (examples):

   macOS

   export RESOLVE_SCRIPT_API="/Library/Application Support/Blackmagic Design/DaVinci Resolve/Developer/Scripting" export RESOLVE_SCRIPT_LIB="/Applications/DaVinci Resolve/DaVinci Resolve.app/Contents/Libraries/Fusion/fusionscript.so" export PYTHONPATH="$PYTHONPATH:$RESOLVE_SCRIPT_API/Modules/"

   Windows (PowerShell)

   $env:RESOLVE_SCRIPT_API='C:\ProgramData\Blackmagic Design\DaVinci Resolve\Support\Developer\Scripting' $env:RESOLVE_SCRIPT_LIB='C:\Program Files\Blackmagic Design\DaVinci Resolve\fusionscript.dll' $env:PYTHONPATH+="$env:PYTHONPATH;${env:RESOLVE_SCRIPT_API}\Modules"

5. Install optional MCP SDK (if not using the bundled requirements): pip install git+https://github.com/modelcontextprotocol/python-sdk.git

6. Launch the MCP server python -m davinci_resolve_mcp

   Or use the provided launcher scripts if present in the repo for your platform

Notes:

• Ensure DaVinci Resolve is running before starting the MCP server.
• If you encounter environment variable issues, run the repository's pre-launch checks or consult INSTALL.md for troubleshooting.

Tips and common issues:

• Make sure DaVinci Resolve is running and that the Resolve scripting API paths are correctly configured for your OS.
• If the server fails to connect to Resolve, verify that the PYTHONPATH includes the Modules directory from RESOLVE_SCRIPT_API.
• Use the config-templates directory to tailor client integration (Cursor/Claude) and adjust server names as needed.
• Check logs at scripts/cursor_resolve_server.log (or equivalent) for detailed error messages.
• On Windows, prefer forward slashes in configuration files to avoid path parsing issues.
• The MCP server supports multiple clients; you can configure separate mcpServers entries for Cursor and Claude if needed.