
DaVinci Resolve Local Bridge MCP
io.github.Airta-AdminPublished by GitHub account Airta-Adminv1.0.0Updated Oct 24, 2026
Control DaVinci Resolve from any AI assistant. 215 MCP tools covering the full Resolve API.
The publisher's own server: Resolve
Overview
A local MCP server that lets an AI assistant control DaVinci Resolve — projects, media, timelines, Fusion, color and rendering — through a bridge running inside
- What you can do
- Check bridge status, Resolve version, active page and switch pages or layout presets, and import or export render presets and burn-in presets. Create, load, save, close, delete, import, export and archive projects and project folders, and read or change project settings and presets. Browse storage volumes and folders, import media, manage media pool folders and clips, relink or unlink clips, and export metadata. Create, rename, duplicate and delete timelines, append clips, detect scene cuts, generate subtitles from audio, and export or import timelines. Manage tracks and timeline items: names, properties, colors, flags, markers, takes, generators, titles, stills, compound and Fusion clips, L
- When to use it
- Use it when you want an AI assistant to drive an editing session in DaVinci Resolve on the same machine — setting up projects and timelines, organizing media, adjusting clips and grades, or queuing renders — instead of clicking through the interface yourself.
- Requirements
- DaVinci Resolve 18.5 or later (Free or Studio) and Python 3.10+ on the same machine. Install the Workflow Integration launcher and bridge script into Resolve, install the Python dependencies, register the server as a stdio process in the assistant's config, and start the bridge from Workspace → Workflow Integrations so it listens on localhost port 8787.
Installation
In SourceWeft
- Open DaVinci Resolve Local Bridge MCP in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Davinc-Resolve-Local-Bridge-MCP
[DaVinci Resolve Local Bridge MCP]
Control DaVinci Resolve from any AI assistant — Claude, Cursor, Devin, and more.
218 tools. Resolve API and optional-extension coverage. Works with DaVinci Resolve Free and Studio.
What Is This?
Davinc-Resolve-Local-Bridge-MCP is a Model Context Protocol (MCP) server that gives AI assistants controlled access to DaVinci Resolve. It exposes 218 tools covering projects, timelines, media, Fusion, color grading, rendering, and supported optional extensions.
How It Works
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 Workflow Integration and Bridge
Run the installer:
The installer adds the user-facing launcher under Workspace → Workflow Integrations and installs the underlying bridge script. Restart Resolve once after installation so it discovers the integration.
For a manual installation, copy workflow/DaVinci Resolve Local Bridge MCP Server Connection.py and the workflow/assets directory to Resolve's Workflow Integration Plugins directory. Also copy bridge/Bridge-Connection-Script.py to Resolve's scripts folder as DaVinciResolveBridge.py. The Scripts entry is retained as a fallback, not the normal launch path.
Step 2 — Install MCP Server Dependencies
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:
Cursor
Edit .cursor/mcp.json:
Devin
Edit mcp_config.json:
Claude Code
Any MCP Client (generic)
The server uses stdio transport. Launch it with:
Step 4 — Start the Bridge Inside DaVinci Resolve
- Open DaVinci Resolve
- Go to Workspace → Workflow Integrations → DaVinci Resolve Local Bridge MCP Server Connection
- Click Start Bridge
- Confirm that the panel reports Running on http://127.0.0.1:8787 (218 actions). For diagnostic details, open Workspace → Console and look for:
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. The supported Workflow Integration launcher starts it for the user; Workspace → Scripts → DaVinciResolveBridge remains available only as a fallback. It:
- Obtains the live
resolveobject from Fusion's globals - Starts an HTTP server on
127.0.0.1:8787 - Exposes 3 endpoints:
GET /health— check if the bridge is aliveGET /actions— list all available action namesPOST /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 218 actions from the bridge's
/actionsendpoint - 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 218 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)
Optional open-source extensions (3 tools)
OpenCaptions and Rembg-Fuse are independent third-party projects and are not bundled with this package.
DaVinci Resolve Local Bridge MCP Server Connection
install.py also installs a supported Workflow Integration launcher. After restarting Resolve once, open Workspace → Workflow Integrations → DaVinci Resolve Local Bridge MCP Server Connection for Start Bridge, Stop Bridge, Refresh Status, and an optional one-time $5 Developer Tip button that opens Stripe-hosted checkout in the default browser. Resolve's public scripting API does not support injecting arbitrary buttons into its native top menu bar; Workflow Integrations is the supported persistent menu surface.
Support development
Leave an optional one-time $5 developer tip
Secure checkout is hosted by Stripe. A tip supports continued development and maintenance of this open-source bridge; it is not a charitable donation or tax-deductible contribution.
Troubleshooting
Bridge won't start
- Make sure DaVinci Resolve is running and a project is open
- Open Workspace → Workflow Integrations → DaVinci Resolve Local Bridge MCP Server Connection and click Start Bridge
- Check the Console (Workspace → Console) for error messages
- Restart DaVinci Resolve after installation — it scans Workflow Integrations at startup
- If the Workflow Integration cannot be opened, use Workspace → Scripts → DaVinciResolveBridge as a fallback and report the integration error
"Could not connect to Resolve Bridge"
- Open Workspace → Workflow Integrations → DaVinci Resolve Local Bridge MCP Server Connection and verify that its status says Running
- 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.exeprocesses can hold the port)
Tools return errors
- Call
resolve_statusfirst 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.
Source: README.md at commit 29cf52c
Tools
0Version history
1- v1.0.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Resolve integrations
Resolve
ai.resolveOfficial publisher
Resolve is a remote AI DevOps investigation server that lets an assistant investigate alerts, run root-cause analysis and answer production questions across…

ResolveMCP-ext
Published by GitHub account CaptRauti
MCP server that gives an assistant DaVinci Resolve 21.1.2 scripting features the mainstream Resolve MCP servers lack: clip effects, Paste Attributes, frame…

DaVinci Resolve
Published by GitHub account Aedelon
MCP server that lets an AI assistant edit, grade and deliver in DaVinci Resolve through typed, verified scripting-API actions.

DaVinci Resolve MCP (free edition)
Published by GitHub account kingjamesch
Drives DaVinci Resolve 21.1 (free or Studio) on macOS through a Lua bridge, letting an assistant manage projects, timelines, media and renders.

Nigeria Bank Resolve MCP by Wycord
Published by GitHub account wycord
Resolves a Nigerian bank account number and bank code to the registered account name, and lists Nigerian banks with their codes.