Official · MODEL CONTEXT PROTOCOL
apvlv davinci resolve mcp
A Model Context Protocol (MCP) server for interacting with DaVinci Resolve and Fusion
WHAT IT CONNECTS
What apvlv davinci resolve mcp gives an AI Agent
- Two-way communication: Connect Claude AI to DaVinci Resolve through the MCP protocol
- Project management: Create, open, and manage DaVinci Resolve projects
- Timeline manipulation: Create, modify, and navigate timelines
- Media management: Import, organize, and manage media in the Media Pool
- Fusion integration: Create and modify Fusion compositions
- Scene inspection: Get detailed information about the current DaVinci Resolve project
- Code execution: Run arbitrary Python code in DaVinci Resolve from Claude
- DaVinci Resolve Studio (version 17 or higher recommended)
- Python 3.8 or higher
- Claude Desktop (for AI integration)
- Clone this repository:
- Install the required dependencies:
- Install the MCP server in Claude Desktop:
- Start DaVinci Resolve
- In Claude Desktop, connect to the "DaVinci Resolve MCP" server
- You can now interact with DaVinci Resolve through Claude
- Install 5ire from [GitHub](https://github.com/nanbingxyz/5ire) or using Homebrew on macOS:
- Start DaVinci Resolve
- In 5ire, add the DaVinci Resolve MCP server
- Connect to the server using your preferred AI model (OpenAI, Claude, etc.)
- You can now interact with DaVinci Resolve through 5ire
- `project://current` - Get information about the current project
- `project://timelines` - Get a list of timelines in the current project
- `timeline://current` - Get information about the current timeline
- `mediapool://folders` - Get a list of folders in the media pool
- `mediapool://current` - Get information about the current media pool folder
- `storage://volumes` - Get a list of mounted volumes in the media storage
- `system://status` - Get the current status of the DaVinci Resolve connection
- `create_project(name)` - Create a new DaVinci Resolve project
- `load_project(name)` - Load an existing DaVinci Resolve project
- `save_project()` - Save the current DaVinci Resolve project
- `create_timeline(name)` - Create a new timeline in the current project
- `set_current_timeline(index)` - Set the current timeline by index (1-based)
- `import_media(file_paths)` - Import media files into the current media pool folder
- `create_folder(name)` - Create a new folder in the current media pool folder
- `create_timeline_from_clips(name, clip_indices)` - Create a new timeline from clips in the current media pool folder
- `add_fusion_comp_to_clip(timeline_index, track_type, track_index, item_index)` - Add a Fusion composition to a clip in the timeline
- `create_fusion_node(node_type, parameters)` - Create a specific Fusion node in the current composition
- `create_fusion_node_chain(node_chain)` - Create a chain of connected Fusion nodes in the current composition
- `open_page(page_name)` - Open a specific page in DaVinci Resolve (media, edit, fusion, color, fairlight, deliver)
- `execute_python(code)` - Execute arbitrary Python code in DaVinci Resolve
- `execute_lua(script)` - Execute a Lua script in DaVinci Resolve's Fusion
- "Create a new project named 'My Documentary'"
- "Import all video files from the Downloads folder"
- "Create a new timeline with the selected clips"
- "Apply a Fusion effect to the selected clip"
- "Get information about the current project"
- "Switch to the Color page"
- "Save the current project"
- "Create a folder named 'Raw Footage' in the media pool"
- "Create a Blur node in the current Fusion composition"
- "Create a Text node with the content 'Hello World'"
- "Create a chain of nodes: MediaIn -> Blur -> ColorCorrector -> MediaOut"
SECURITY
An MCP listing is not a security review
An MCP server may receive model context, credentials, local files, or permission to call external systems. Review its code, requested environment variables, network behavior, package provenance, and maintenance status before connecting it to an agent.
README
Repository documentation
Model Context Protocol (MCP) server that lets MCP clients control and inspect DaVinci Resolve (including Fusion) through tools and resources.
- Project management (create, load, save)
- Timeline operations (create timeline, switch timeline, build from clips)
- Media pool operations (import media, create folders, inspect folders)
- Fusion helpers (add comp to clip, create nodes, create node chains)
- Resolve page navigation
- Advanced scripting (
execute_python,execute_lua)
- Python 3.10+
- DaVinci Resolve with scripting API available
- An MCP-compatible client (for example Claude Desktop)
git clone https://github.com/apvlv/davinci-resolve-mcp.git
cd davinci-resolve-mcp
uv sync --all-extras --devuv run davinci-resolve-mcpThe server will try to connect to Resolve on startup. Make sure DaVinci Resolve is running.
Configure your MCP client to launch the server command:
{
"mcpServers": {
"davinci-resolve": {
"command": "uv",
"args": ["run", "davinci-resolve-mcp"]
}
}
}system://statusproject://currentproject://timelinestimeline://currentmediapool://foldersmediapool://currentstorage://volumes
create_project(name)load_project(name)save_project()
create_timeline(name)set_current_timeline(index)
import_media(file_paths)create_folder(name)create_timeline_from_clips(name, clip_indices)
add_fusion_comp_to_clip(timeline_index, track_type, track_index, item_index)create_fusion_node(node_type, parameters)create_fusion_node_chain(node_chain)
open_page(page_name)where page name is one of:media,edit,fusion,color,fairlight,deliver
execute_python(code)execute_lua(script)
make install # install deps and pre-commit hooks
make lint-check # ruff check
make format-check # ruff format check
make test # pytest with coverage
make check # lint + format + tests- "Create a project named
My Documentary" - "List timelines in the current project"
- "Import these files into the media pool"
- "Open the Color page"
- "Create a Fusion node chain Blur -> ColorCorrector"
MIT (see LICENSE)
COMMUNITY
Save, rate, and discuss
Loading community data…