Svetovid
Allows an AI agent to interact with DaVinci Resolve Studio, enabling it to see the current frame, edit timelines, and manage projects.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@SvetovidRender the current frame so I can see what's on the timeline."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Svetovid
An MCP server that lets your agent see and edit video inside DaVinci Resolve Studio.
Requires DaVinci Resolve Studio (the scripting API is Studio only)
Svetovid wires an AI agent into DaVinci Resolve. The agent can orient itself in your project, see the frame at the playhead, and assemble, grade and render on the timeline, working alongside you in the same project.
Named for the four faced Slavic god who watches in all directions. Svet is light, vid is sight, the same ancient root that gives us the word video.
Why
Most tooling drives an editor blind, pushing metadata it cannot see. Svetovid is built perception first: the agent renders the actual frame and looks at it, so it edits against what is really on screen, not a guess.
Related MCP server: DaVinci Resolve MCP Server
Requirements
DaVinci Resolve Studio 18.5 or newer, running.
External scripting enabled: Resolve, Preferences, System, General, External scripting using set to Local.
Python 3.10 or newer.
Install
pip install -e .Wire into Claude Code
claude mcp add svetovid -- svetovid-mcpOr any MCP client, by running svetovid-mcp as the server command.
Tools
Tool | What it does |
| Orient. Returns the open project, the current timeline, frame rate, resolution, track counts and clip count. Call this first. |
| See the edit. Exports the frame at the playhead and returns it as an image. |
More tools land as the build grows: media import, timeline assembly, markers, render and export.
Environment
Resolve's scripting paths are auto-detected per platform. Override them in a .env only for a non-standard install (see .env.example).
License
MIT. Built for personal use, shared openly, never productised.
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/hello-emrah/svetovid-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server