Resolve MCP
Provides tools for automating DaVinci Resolve Studio video editing, including project and timeline inspection, media import, timeline editing (cut, trim, ripple delete, markers, titles), clip property adjustments, timeline export, and visual verification through rendered frames and screenshots.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Resolve MCP
A production-ready Model Context Protocol (MCP) server that connects AI assistants like Claude to DaVinci Resolve Studio for professional video editing automation.
Features
Project Inspection: Get project info, timelines, tracks, clips, and media pool contents
Media Import: Import media files into the media pool with folder organization
Timeline Editing: Cut, trim, ripple delete, add markers, and Text+ titles
Clip Properties: Adjust opacity, volume, transform, speed, and color grade
Timeline Management: Duplicate timelines, export to EDL/FCPXML/OTIO
Visual Verification: Render frames and take screenshots for AI visual verification
Safety First: Approval system for destructive actions
Cross-Platform: macOS, Windows, and Linux support
MCP Compatible: Works with Claude Desktop and other MCP clients
Related MCP server: DaVinci Resolve MCP Server
Installation
Via npx (Recommended)
npx resolve-mcpGlobal Install
npm install -g resolve-mcp
resolve-mcpClaude Desktop Configuration
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"resolve-mcp": {
"command": "npx",
"args": ["resolve-mcp"],
"env": {}
}
}
}Requirements
Node.js 20+
Python 3.8+ (for the Resolve bridge)
DaVinci Resolve Studio 18+ (Free version has limited scripting support)
DaVinci Resolve running with a project open
Usage
Start the MCP Server
# Default (stdio transport for MCP clients)
npx resolve-mcp
# Test connection
npx resolve-mcp test
# System check
npx resolve-mcp doctor
# With auto-approve (testing only)
npx resolve-mcp serve --auto-approveAvailable Tools
Once connected to an MCP client (like Claude), you can use these tools:
Project & Timeline Inspection
get_project_info- Get full project detailsget_timeline_info- Get specific timeline detailslist_timelines- List all timelinesget_media_pool- Get media pool contentssearch_media_pool- Search for clips
Media Import
import_media- Import media files
Editing Operations
cut_clip- Cut a clip at a specific frametrim_clip- Trim clip start/end with optional rippleripple_delete- Remove timeline section with ripple editadd_marker- Add markers to timelineadd_text_title- Add Text+ titlesduplicate_timeline- Duplicate a timelineadjust_clip_properties- Adjust clip properties
Export
export_timeline- Export to EDL, FCPXML, or OTIO
Visual Verification
render_frame- Render a single frametake_screenshot- Take timeline viewer screenshotget_resolve_version- Get Resolve version info
Example Workflows
Basic Editing with Claude
User: "Open my project and show me the timeline structure"
Claude: [Calls get_project_info, lists timelines and tracks]
User: "Cut the clip at 00:01:30 and add a marker called 'Scene Change'"
Claude: [Calls cut_clip and add_marker with approval]
User: "Export the timeline as FCPXML for Final Cut Pro"
Claude: [Calls export_timeline with format: fcpXML]Visual Verification
User: "Show me frame 1500 of the timeline to verify the cut"
Claude: [Calls render_frame, returns image for visual verification]
User: "Take a screenshot at 00:02:15:10"
Claude: [Calls take_screenshot with timecode]Safety & Approval System
All destructive operations require explicit approval:
High Risk: Ripple delete, trim with ripple, color grade changes
Medium Risk: Cut, trim, markers, titles, duplicate, property adjustments, export, import
Low Risk: Read-only operations (project info, timeline info, media pool)
The approval system integrates with MCP clients to prompt users before executing risky operations.
Architecture
┌─────────────────┐ MCP Protocol ┌──────────────────┐
│ AI Assistant │ ◄────────────────────► │ Resolve MCP │
│ (Claude, etc.) │ stdio/JSON-RPC │ Server (Node.js)│
└─────────────────┘ └────────┬─────────┘
│
spawn/stdin
▼
┌──────────────────────┐
│ Python Bridge │
│ (resolve_bridge.py) │
└──────────┬───────────┘
│
Resolve Scripting API
▼
┌──────────────────────┐
│ DaVinci Resolve │
│ Studio │
└──────────────────────┘Development
# Install dependencies
npm install
# Build
npm run build
# Development mode with hot reload
npm run dev
# Run tests
npm test
# Lint
npm run lintProject Structure
resolve-mcp/
├── src/
│ ├── index.ts # Main exports
│ ├── cli.ts # CLI entry point
│ ├── types/index.ts # TypeScript types
│ ├── server/mcp-server.ts # MCP server implementation
│ ├── bridge/bridge-client.ts # Python bridge client
│ └── utils/approval.ts # Approval system
├── bridge/
│ └── resolve_bridge.py # Python Resolve bridge
├── tests/ # Test files
├── dist/ # Compiled output
├── package.json
├── tsconfig.json
└── README.mdDaVinci Resolve Scripting Setup
macOS
The scripting module is installed with Resolve at:
/Library/Application Support/Blackmagic Design/DaVinci Resolve/Developer/Scripting/ModulesWindows
C:\ProgramData\Blackmagic Design\DaVinci Resolve\Support\Developer\Scripting\ModulesLinux
/opt/resolve/Developer/Scripting/ModulesEnsure the DaVinciResolveScript.py module is in your Python path, or the bridge will auto-detect it.
Troubleshooting
"Could not connect to DaVinci Resolve"
Ensure DaVinci Resolve is running
Ensure a project is open
Check that the scripting module is accessible
"DaVinci Resolve scripting module not found"
Verify Resolve Studio is installed (Free version has limited API)
Check the platform-specific paths above
Try running
python3 -c "import DaVinciResolveScript"
Permission denied on bridge script
chmod +x bridge/resolve_bridge.pyLicense
MIT License - see LICENSE file for details.
Contributing
Fork the repository
Create a feature branch
Make your changes
Run tests and linting
Submit a pull request
Support
Issues: GitHub Issues
Documentation: This README
MCP Spec: https://modelcontextprotocol.io
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Generate, extend and edit AI images and videos, then assemble clips on a timeline and render.
AI video editor for agents and humans: timeline, captions, color, audio and generation as MCP tools.
The agentic video editor for ChatGPT and Claude. Ask in your chat and it cuts, captions, adds music, titles and motion graphics on a real timeline you can open and adjust.
AI video editor your agent can drive: plan scenes, edit a multi-track timeline, and render MP4s.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI assistants to control DaVinci Resolve (Free and Studio) through 215 MCP tools covering the full Resolve scripting API, including projects, timelines, media, Fusion, color, and rendering.171 PyPI1MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to control DaVinci Resolve Studio through the official Scripting API, covering editing, media pool management, rendering, grading, Fusion, Fairlight, and project lifecycle tasks.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to control DaVinci Resolve Studio through the official Scripting API, covering editing, media pool, render, grading, Fusion, Fairlight, and project lifecycle tasks.9,499 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to inspect and control DaVinci Resolve on the local machine, including listing projects, timelines, and media, switching pages, and, when write access is enabled, importing media, building timelines, adding titles and markers, saving projects, and rendering.MIT