This MCP server establishes two-way communication between AI assistants like Claude and DaVinci Resolve, allowing you to control Resolve's functions through natural language commands. The server provides extensive capabilities for project management, timeline editing, media operations, and Fusion composition directly from your AI assistant.
Clone the repository:
git clone https://github.com/apvlv/davinci-resolve-mcp.git
cd davinci-resolve-mcp
Install required dependencies:
pip install -r requirements.txt
Install the MCP server in Claude Desktop:
mcp install src/resolve_mcp/server.py
5ire is an open-source desktop AI assistant compatible with this MCP server.
brew tap brewforge/extras
brew install --cask 5ire
project://current
- Get information about the current projectproject://timelines
- List all timelines in the current projecttimeline://current
- Get information about the current timelinemediapool://folders
- List all folders in the media poolmediapool://current
- Get information about the current media pool folderstorage://volumes
- List mounted volumes in media storagesystem://status
- Check DaVinci Resolve connection statuscreate_project(name)
- Create a new projectload_project(name)
- Open an existing projectsave_project()
- Save the current projectcreate_timeline(name)
- Create a new timelineset_current_timeline(index)
- Switch to a specific timelineimport_media(file_paths)
- Import media filescreate_folder(name)
- Create a new media pool foldercreate_timeline_from_clips(name, clip_indices)
- Create timeline from selected clipsadd_fusion_comp_to_clip(timeline_index, track_type, track_index, item_index)
- Add Fusion composition to a clipcreate_fusion_node(node_type, parameters)
- Create a Fusion nodecreate_fusion_node_chain(node_chain)
- Create connected Fusion nodesopen_page(page_name)
- Navigate to specific pages (media, edit, fusion, color, fairlight, deliver)execute_python(code)
- Run Python code in DaVinci Resolveexecute_lua(script)
- Run Lua script in FusionHere are some example interactions you can use with the MCP server:
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.