Skip to main content
Glama

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

npx resolve-mcp

Global Install

npm install -g resolve-mcp
resolve-mcp

Claude 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-approve

Available Tools

Once connected to an MCP client (like Claude), you can use these tools:

Project & Timeline Inspection

  • get_project_info - Get full project details

  • get_timeline_info - Get specific timeline details

  • list_timelines - List all timelines

  • get_media_pool - Get media pool contents

  • search_media_pool - Search for clips

Media Import

  • import_media - Import media files

Editing Operations

  • cut_clip - Cut a clip at a specific frame

  • trim_clip - Trim clip start/end with optional ripple

  • ripple_delete - Remove timeline section with ripple edit

  • add_marker - Add markers to timeline

  • add_text_title - Add Text+ titles

  • duplicate_timeline - Duplicate a timeline

  • adjust_clip_properties - Adjust clip properties

Export

  • export_timeline - Export to EDL, FCPXML, or OTIO

Visual Verification

  • render_frame - Render a single frame

  • take_screenshot - Take timeline viewer screenshot

  • get_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 lint

Project 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.md

DaVinci Resolve Scripting Setup

macOS

The scripting module is installed with Resolve at:

/Library/Application Support/Blackmagic Design/DaVinci Resolve/Developer/Scripting/Modules

Windows

C:\ProgramData\Blackmagic Design\DaVinci Resolve\Support\Developer\Scripting\Modules

Linux

/opt/resolve/Developer/Scripting/Modules

Ensure 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.py

License

MIT License - see LICENSE file for details.

Contributing

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes

  4. Run tests and linting

  5. Submit a pull request

Support

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers