Schema | DaVinci Resolve MCP Bridge

DaVinci Resolve MCP Bridge

Describes the environment variables required to run the server.

Name	Required	Description	Default
`DAVINCI_RESOLVE_BRIDGE`	No	Set to 1 to force the server to use only the in-app Resolve bridge.
`DAVINCI_RESOLVE_MCP_MOTION_GL`	No	WebGL backend for motion graphics: angle (default on Mac and Windows), swangle (default on Linux), egl or vulkan.	angle
`DAVINCI_RESOLVE_MCP_MOTION_OUT`	No	Where motion graphics renders go.	motion-graphics/out/
`DAVINCI_RESOLVE_MCP_VISION_URL`	No	URL of any OpenAI-compatible vision server (use http://127.0.0.1:11434/v1 for Ollama).	http://127.0.0.1:1234/v1
`DAVINCI_RESOLVE_MCP_MOTION_ENTRY`	No	Entry file of your own Remotion project, used together with DAVINCI_RESOLVE_MCP_MOTION_PROJECT.
`DAVINCI_RESOLVE_MCP_VISION_MODEL`	No	Which vision model to use for frame descriptions. If not set, a loaded vision model is picked automatically.	auto
`DAVINCI_RESOLVE_MCP_WHISPER_MODEL`	No	Whisper model size used by the local_ai transcription tool. Can be tiny, base, small, medium, large-v3 or turbo.	base
`DAVINCI_RESOLVE_MCP_MOTION_BROWSER`	No	Path to a Chrome or Chromium binary, if Remotion's download is blocked.
`DAVINCI_RESOLVE_MCP_MOTION_PROJECT`	No	Use your own Remotion project for the motion_graphics tool instead of the bundled templates.
`DAVINCI_RESOLVE_MCP_WHISPER_DEVICE`	No	Device used for Whisper transcription: cpu, cuda or auto.	auto

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityActive

ResponsivenessNo issues