Svetovid
You can orient yourself inside a live DaVinci Resolve Studio project and visually see what the timeline is showing at the playhead.
Orient in Resolve (
get_state): returns product and version, the open project, every timeline, and for the current timeline its frame rate, resolution, track counts, clip count and frame range. Intended to be called first.See the edit (
render_current_frame): exports the frame at the playhead and returns it as an image, so you can look at what the timeline actually shows before and after an edit rather than reasoning from metadata alone.
Note: the README describes 89 tools across seeing/navigating, project, media, timeline, edit/assembly, transforms, markers, colour, audio and render/deliver, but the supplied schema exposes only these two.
Allows an AI agent to interact with DaVinci Resolve Studio, enabling it to see the current frame, edit timelines, and manage projects.
Click on "Deploy 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., "@Svetovid Render 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.
Resolve MCP
Formerly Svetovid.
An MCP server for seeing and editing video in DaVinci Resolve Studio.
It does the one thing most editing tools for agents cannot: see.
Resolve MCP is a Model Context Protocol server for DaVinci Resolve Studio. Most tools drive an editor blind, pushing metadata they cannot see. Resolve MCP renders the frame at the playhead and hands it back, so the agent works from what is really on screen, not a guess. It speaks to Resolve over its scripting API, and you and the agent share the same open project. Built for personal use, shared openly, not productised.
Runs on your machine, alongside your open Resolve project.
Tools
Eighty nine tools spanning the Resolve scripting API, from orienting in a project to delivering the final file. The two at the top are the heart: Resolve MCP renders the real frame so the agent edits against what is on screen, not blind metadata. Everything destructive sits behind a confirm gate, the tool previews the action and only applies it when called again with confirm set, so a first exploratory call never deletes work or starts a render.
Group | Tools |
See and navigate |
|
Project |
|
Media |
|
Timeline |
|
Edit and assembly |
|
Clip transforms |
|
Markers |
|
Colour |
|
Audio |
|
Render and deliver |
|
Every tool returns plain data the agent can read, and reaches Resolve through the shared scaffolding in connection.py (the live handle), gate.py (the confirm gate) and serialize.py (objects to plain dicts). One module per group under src/resolve_mcp/tools/.
Related MCP server: video-editor
Requirements
DaVinci Resolve Studio 18.5 or newer, running. The scripting API is Studio only.
External scripting enabled: Resolve, Preferences, System, General, External scripting using set to Local.
Python 3.10 or newer.
Install
git clone https://github.com/hello-emrah/resolve-mcp.git
cd resolve-mcp
pip install -e .Wire into Claude Code
Add an entry to ~/.claude.json under mcpServers:
{
"mcpServers": {
"resolve": {
"command": "resolve-mcp"
}
}
}Restart Claude Code. The tools appear under the mcp__resolve__* namespace.
Environment
Resolve's scripting paths are auto-detected per platform. Set RESOLVE_SCRIPT_API and RESOLVE_SCRIPT_LIB in a .env only for a non-standard install (see .env.example).
Design philosophy
The visual mark and the tool itself were built deliberately against the visual language of capitalist software design. No gradients, no neon, no glass, no drop shadows, no isometric stock illustration. Single-shade flat seals in warm earth tones, ancient-glyph silhouettes, generous whitespace. The mark could be pressed into wax or carved into stone.
This tool is built for personal use and shared openly. It is not productised, monetised, or instrumented. Use it for your own work or fork it for yours.
License
MIT, see LICENSE.
Available Tools
2 toolsget_stateA
Orient in DaVinci Resolve. Call this first.
Returns the product and version, the open project, every timeline in the project, and for the current timeline its frame rate, resolution, track counts, clip count and frame range.
Inputs: no named parameters.
render_current_frameA
See the edit. Export the frame at the playhead and return it as an image.
Use this to look at what the timeline actually shows before and after an edit, rather than reasoning from metadata alone. The current timeline must be open and a frame visible at the playhead.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools serve clearly distinct purposes: one provides project and timeline metadata, the other exports a frame as an image. There is no overlap or ambiguity.
Both tools follow a consistent verb_noun snake_case pattern: get_state and render_current_frame. Naming is uniform and predictable.
With only 2 tools for a complex domain like DaVinci Resolve, the server feels significantly underdeveloped. While it covers basic inspection and frame export, many essential operations (e.g., editing, timeline manipulation) are missing.
The server provides only state retrieval and frame rendering, lacking any editing or modification capabilities. For a tool claiming to 'orient' and 'see the edit,' the absence of editing tools makes it incomplete for interactive workflows.
Maintenance
Related MCP Connectors
AI video editor for agents and humans: timeline, captions, color, audio and generation as MCP tools.
AI video editor your agent can drive: plan scenes, edit a multi-track timeline, and render MP4s.
MCP server for Google Veo AI video generation
MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.
Related MCP Servers
- AlicenseBqualityCmaintenanceA local, safety-first MCP server for inspecting, editing, and rendering videos in DaVinci Resolve through natural language prompts.272MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for OmniCut that provides 29 deterministic video editing tools (trim, transition, render, etc.) for AI agents to drive the video editor end-to-end.11 npm1ISC
- AlicenseNot gradedqualityDmaintenanceThe Rendr MCP server allows AI agents to control the full video editing workflow, including recording, timeline editing, color grading, and exporting.AGPL 3.0
- FlicenseNot gradedqualityCmaintenanceMCP server for DaVinci Resolve video editing, enabling AI agents to execute editing operations, manage creative libraries, and analyze media content.-