DaVinci Resolve

Enables AI assistants to interact with DaVinci Resolve Studio for advanced control over video editing, color grading, and audio.

Control DaVinci Resolve Studio from MCP clients such as Claude Desktop.

This project exposes Resolve projects, timelines, media, Fusion, color, audio, playback, and rendering operations through a localModel Context Protocolserver.

git clone https://github.com/Tooflex/davinci-resolve-mcp.git cd davinci-resolve-mcp

winget install --id Python.Python.3.10 -e

& "$env:LOCALAPPDATA\Programs\Python\Python310\python.exe" -m venv .venv310 .\.venv310\Scripts\python.exe -m pip install --upgrade pip .\.venv310\Scripts\python.exe -m pip install -e .

python3.11 -m venv .venv ./.venv/bin/python -m pip install --upgrade pip ./.venv/bin/python -m pip install -e .

python3.11 -m venv .venv ./.venv/bin/python -m pip install --upgrade pip ./.venv/bin/python -m pip install -e . ./.venv/bin/davinci-resolve-mcp

uv pip install --python .venv/bin/python -e .

{ "mcpServers": { "davinci-resolve": { "command": "powershell", "args": [ "-NoProfile", "-ExecutionPolicy", "Bypass", "-File", "C:\\absolute\\path\\to\\davinci-resolve-mcp\\run_server.ps1" ] } } }

Edit~/Library/Application Support/Claude/claude_desktop_config.json:

{ "mcpServers": { "davinci-resolve": { "command": "/absolute/path/to/davinci-resolve-mcp/.venv/bin/davinci-resolve-mcp", "args": [] } } }

Use the same command and argument pairs shown above:

- Windows:powershell -NoProfile -ExecutionPolicy Bypass -File <run_server.ps1>
- macOS/Linux:<venv>/bin/davinci-resolve-mcp

Use absolute paths. Keep Resolve running, restart the MCP client after changing its configuration, and then check that thedavinci-resolvetools are available.

execute_luaruns code inside Resolve. Only execute scripts from sources you trust.

server.pyimportsresolve_env.pybefore creatingResolveAPI.
- selects the Resolve scripting API and native library paths;
- propagates the selected Modules directory to child processes;
- probesDaVinciResolveScriptin a disposable subprocess;
- imports the native library in the MCP process only when the probe exits safely.

On Windows, Resolve may otherwise select a Python runtime from the Windows registry and load a foreignpython3xx.dllinto the current process.FUSION_PYTHON3_HOME, DLL preloading, and the isolated launcher prevent that native crash.

Defaults work for standard Resolve installations. For a custom installation, set these variables before starting the server:

export RESOLVE_SCRIPT_PATH="/custom/Developer/Scripting/Modules" export RESOLVE_SCRIPT_API="/custom/Developer/Scripting" export RESOLVE_SCRIPT_LIB="/custom/Fusion/fusionscript.so" ./.venv/bin/davinci-resolve-mcp

- Confirm that DaVinci Resolve Studio is running.
- SetExternal scripting usingtoLocal, then restart Resolve.
- Confirm that the configured Python is version 3.10 or 3.11.
- Check that the Resolve scripting Modules directory exists.

The server intentionally remains available in a disconnected state when it cannot initialize Resolve.

scriptapp('Resolve') returned None

The native module loaded, but it could not obtain a running Resolve object. Resolve is either closed, external scripting is disabled, or the installed edition does not support external scripting.

ModuleNotFoundError: No module named 'imp'

Python 3.12 or newer is being used. Recreate the virtual environment with Python 3.10 or 3.11.

Launch the project throughrun_server.ps1, not withpython server.py.

The crash occurs whenfusionscript.dllloads an incompatible Python runtime, often from another python.org or Anaconda installation registered on the machine. The launcher setsFUSION_PYTHON3_HOMEand isolates DLL resolution.

No valid Resolve scripting module path found

SetRESOLVE_SCRIPT_PATHto the directory containingDaVinciResolveScript.py. If the native library is also in a non-standard location, setRESOLVE_SCRIPT_LIB.

Install the project into the same interpreter configured in the MCP client:

python -m py_compile server.py resolve_api.py resolve_env.py

The GitHub Actions workflow runs the unit tests on Python 3.10 and 3.11 across Windows, macOS, and Linux.

Contributions should keep platform-specific bootstrap behavior covered by tests.

The World's First AI Music MCP Beyond images and video, your agent can now generate music.

Transcribe and summarize video content from links using various transcription services.

: MCP server for AI media generation (imagesflux, videosveo3.1, music suno v5, with deterministic cost control using reserve-burn-refund billing

Create AI music videos and audio-reactive visuals from songs through MCP.

Turn any language model into a multimodal powerhouse that can generate images, music, videos and more on the fly. Rostro's tools are designed to be used by language models from the ground up, expanding capabilities with minimal context bloat.

All-in-one AI creative studio — generate videos, images, audio in 11 Indian languages, and 3D models via MCP. Hosted at mcp.arcframe.ai.

Official Cannon Studio MCP for AI video, image, 3D, audio, workflow, pricing, model, and developer API guidance.

A server for creating fast and free lipsync videos for digital avatars, supporting both realistic and cartoon styles.

MCP server for AI image, video, voice and music generation, routing prompts to Veo 3.1, Seedance 2.0, Nano Banana 2, GPT-Image-2 and more, from Claude, Cursor, ChatGPT or Codex.

Audio tools MCP server for professional audio editing and AI augmentation