Davinc Resolve Local Bridge MCP Server

Davinc-Resolve-Local-Bridge-MCP

---

What Is This?

Davinc-Resolve-Local-Bridge-MCP is a Model Context Protocol (MCP) server that gives AI assistants full control over DaVinci Resolve. It exposes 215 tools covering the entire Resolve scripting API — projects, timelines, media, Fusion, color grading, rendering, and more.

How It Works

Your AI Assistant (Claude, Cursor, Devin, etc.)
       │
       │  talks MCP (stdio)
       ▼
  mcp_server/server.py        ← runs on your machine
       │
       │  talks HTTP (localhost:8787)
       ▼
  Bridge-Connection-Script.py ← runs INSIDE DaVinci Resolve
       │                        (Workspace > Scripts menu)
       ▼
  DaVinci Resolve API         ← full read + write access

The bridge script runs inside DaVinci Resolve's process, giving it full access to the Resolve scripting API — even on the Free edition (which blocks external scripting). The MCP server runs as a separate process and proxies tool calls to the bridge over localhost HTTP.

---

Quick Start

Prerequisites

• DaVinci Resolve 18.5+ (Free or Studio)
• Python 3.10+ on your machine
• An MCP-compatible AI assistant (Claude Desktop, Cursor, Devin, etc.)

Step 1 — Install the Bridge Script

Run the installer:

python install.py

Or manually copy bridge/Bridge-Connection-Script.py to Resolve's scripts folder:

Step 2 — Install MCP Server Dependencies

pip install -r requirements.txt

Step 3 — Configure Your AI Assistant

Add the MCP server to your assistant's configuration file. The server path is mcp_server/server.py in this repo.

Claude Desktop

Edit claude_desktop_config.json:

{
  "mcpServers": {
    "davinci-resolve-local-bridge": {
      "command": "python",
      "args": ["C:/path/to/Davinc-Resolve-Local-Bridge-MCP/mcp_server/server.py"]
    }
  }
}

Cursor

Edit .cursor/mcp.json:

{
  "mcpServers": {
    "davinci-resolve-local-bridge": {
      "command": "python",
      "args": ["C:/path/to/Davinc-Resolve-Local-Bridge-MCP/mcp_server/server.py"]
    }
  }
}

Devin

Edit mcp_config.json:

{
  "mcpServers": {
    "resolve-local-bridge": {
      "command": "python",
      "args": ["C:/path/to/Davinc-Resolve-Local-Bridge-MCP/mcp_server/server.py"]
    }
  }
}

Claude Code

claude mcp add davinci-resolve-local-bridge -- python C:/path/to/Davinc-Resolve-Local-Bridge-MCP/mcp_server/server.py

Any MCP Client (generic)

The server uses stdio transport. Launch it with:

python mcp_server/server.py

Step 4 — Start the Bridge Inside DaVinci Resolve

1. Open DaVinci Resolve
2. Go to Workspace → Scripts → Bridge-Connection-Script
3. Look in the Console (Workspace → Console) for:

[Resolve Bridge] Connected to Resolve 21.0.4.5
[Resolve Bridge] HTTP server running on http://127.0.0.1:8787
[Resolve Bridge] 215 actions available

Step 5 — Start Using It

Ask your AI assistant:

"Check if DaVinci Resolve is connected"

The assistant will call the resolve_status tool and report back. Then try:

"Create a new 1920x1080 30fps project called 'My Video' and add a timeline"

---

Architecture

Bridge Script (bridge/Bridge-Connection-Script.py)

A Python script that runs inside DaVinci Resolve via the Workspace > Scripts menu. It:

• Obtains the live resolve object from Fusion's globals
• Starts an HTTP server on 127.0.0.1:8787
• Exposes 3 endpoints:
  • GET /health — check if the bridge is alive
  • GET /actions — list all available action names
  • POST /action — execute an action by name with parameters
• Stays alive with a blocking serve_forever() call
• Kills any previous instance on the same port before starting

MCP Server (mcp_server/server.py)

A standalone MCP server that:

• Connects to the bridge over HTTP on localhost
• Auto-discovers all 215 actions from the bridge's /actions endpoint
• Exposes each action as an MCP tool with the resolve_ prefix
• Proxies tool calls to the bridge via POST /action
• Stays in sync with the bridge — no manual tool definitions needed

---

All 215 Tools

The MCP server auto-discovers tools from the bridge. Each tool is prefixed with resolve_ (e.g., status becomes resolve_status). Pass parameters as a params object.

Resolve Application (15 tools)

Project Manager (18 tools)

Project Settings (7 tools)

Media Storage (4 tools)

Media Pool (13 tools)

Timeline (21 tools)

Timeline Tracks (11 tools)

Timeline Items (66 tools)

All item actions accept optional trackType, trackIndex, itemIndex to target a specific clip, or operate on the first selected clip if omitted.

Fusion Compositions (14 tools)

Fusion Tools (11 tools)

Gallery (4 tools)

Color / Nodes (7 tools)

Rendering (22 tools)

Speech & Subtitles (1 tool)

Special (1 tool)

---

Troubleshooting

Bridge won't start

• Make sure DaVinci Resolve is running and a project is open
• Check the Console (Workspace → Console) for error messages
• Restart DaVinci Resolve — it only scans the Scripts folder at startup

"Could not connect to Resolve Bridge"

• Make sure you ran Workspace → Scripts → Bridge-Connection-Script inside Resolve
• Check that the console shows [Resolve Bridge] HTTP server running on http://127.0.0.1:8787
• If the port is already in use, close Resolve and reopen it (stale fuscript.exe processes can hold the port)

Tools return errors

• Call resolve_status first to verify connectivity
• Some actions require a project to be open, a timeline to exist, or a clip to be selected
• Error messages from the bridge indicate what's missing

---

Technical Details

• Bridge port: 127.0.0.1:8787 (localhost only, no external access)
• Transport: HTTP/1.0 with Connection: close
• MCP transport: stdio
• Dependencies: mcp, requests (MCP server only; bridge uses pure stdlib)
• Resolve version: 18.5+ (tested on 21.0.4.5)
• Python: 3.10+ for MCP server; bridge uses Resolve's embedded Python

---

License

MIT License — see LICENSE file.

---

Credits

Created by: A Fellow Coder for fellow coders. Inspired by the DaVinci Resolve scripting community.