DaVinci Resolve MCP Server

Community

MCP server for DaVinci Resolve Studio, enabling AI assistants to fully control post-production workflows via the official scripting API.

How to install ↓ Compare GitHub source repository ↗

Category: Other #8 of 230
Stars: ★ 3.5k Very popular
Transport: stdio (local process)
Runtime: Python 3.10+ · Prebuilt binary
Credentials: No credential needed
License: MIT
Last commit: today
Tools: 10

71FMRS · B

This MCP server offers comprehensive control over DaVinci Resolve Studio, covering 100% of the API methods, with two modes and high test coverage. It is designed for professional post-production, emphasizing source media safety and confirmation for destructive actions.

Strongest · Documentation 18/20 Weakest · Reliability 9/20

Reliability

9/20

Security and permissions

15/20

Maintenance

16/20

Documentation

18/20

Setup experience

13/20

Why each score

Reliability 9/20: Only the README and repository metadata were available; the manifest was not cached, and no CI workflows or test files were supplied. README claims 34/341 tools, 100% API coverage and 96.8% live-tested, but none of this execution evidence can be verified statically. No contradictions are visible, yet reproducible key paths are unproven; per static calibration this must stay at or below 12, so a conservative 9 is given.
Security and permissions 15/20: README states a local stdio default, no network listener, immutable source media, confirmation for destructive operations, and an HMAC-signed loopback bridge with one-use nonces; a security policy is documented. No red-line issues such as malware, credential theft, covert exfiltration, or irreversible defaults without confirmation are evident. However, actual code was not inspected, so permission enforcement and data-flow implementation remain unverified; conservative 15.
Maintenance 16/20: Metadata shows a non-archived repository with only 2 open issues. README includes a clear author, MIT license, version 2.78.1, changelog, release process, and security reporting channels, indicating sound governance. However, no commit history, release dates, or dependency-update records were provided for verification, so sustained maintenance is inferred rather than proven; score 16.
Documentation 18/20: README provides layered documentation: quick start, installation/configuration, server modes, requirements, explicit non-goals, security posture, a documentation index, and examples. It also discloses optional extras and limitations. The quality is high, but advanced claims (live-test rates, control panel, advanced server behavior) cannot be statically verified from the supplied material, so full marks are not given; score 18.
Setup experience 13/20: README details an npx setup command, source install, client configuration examples, platform paths, a free-edition bridge, and a doctor script for dependency checks; the steps are clear. However, setup depends on Resolve Studio (or the bridge), Python 3.10+, and configuring External scripting, so it is not a zero-config install. No CI or committed tests were supplied to demonstrate execution, and static calibration caps setup at 15; conservative 13.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessReads local filesWrites / deletes local filesRuns commands or codeConnects to a database

Best for

Video editing and post-production professionals
Colorists using DaVinci Resolve Studio
Assistant editors needing workflow automation
Teams wanting to integrate AI assistants for media management

Not for

Users relying solely on the free edition of DaVinci Resolve (requires bridge, may be unstable)
Those needing a network service or server-side deployment (local stdio only)
Those wanting automatic selection of the best take (not provided)
Those wanting automatic cutting to music (not provided)

Required permissions

Launch and control DaVinci Resolve application
Read and write Resolve project database
Read and write local media files (for analysis)
Perform destructive actions (with confirmation)
Execute external commands (e.g., ffmpeg)

Risks and side effects

May modify project data; ensure backups
Analysis tools do not modify source media, but may write metadata
Destructive operations require caution
Free edition bridge may be closed by Blackmagic

Setup

Before you start

Runtime：Python 3.10+ · Prebuilt binary

Other optional settings (1)

DAVINCI_RESOLVE_BRIDGE optional Set to 1 to force the in-app bridge (for the free edition) as the only transport instead of automatic fallback; not needed by default.

Open DaVinci Resolve Studio (18.5+), set Preferences > General > External scripting using to 'Local'.
Run npx davinci-resolve-mcp setup or clone the repo and run python install.py.
The installer configures Claude Desktop, Claude Code, Cursor, VS Code, etc.
For the free edition, run python scripts/install_resolve_bridge.py and set DAVINCI_RESOLVE_BRIDGE=1.

claude_desktop_config.json

{
  "mcpServers": {
    "davinci-resolve": {
      "command": "<python>",
      "args": [
        "<path>/src/server.py"
      ]
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json

{
  "servers": {
    "davinci-resolve": {
      "command": "<python>",
      "args": [
        "<path>/src/server.py"
      ]
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal

claude mcp add davinci-resolve -- '<python>' '<path>/src/server.py'

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

After connecting the client, the tool list should show the 34 compound tools (e.g. app_control, media_pool); asking "List all projects" and getting a real project list from Resolve confirms the install works.

Troubleshooting

Check Resolve is set to 'Local' for scripting
Verify Python version is 3.10-3.12 (or newer compatible)
Run `python scripts/doctor.py` to check dependencies
Refer to logs and API coverage docs
If using free edition, confirm bridge is installed and running

Things to try

Once connected, you can ask your AI assistant things like:

List all projects and open the one called 'My Film'
Build a ProRes 422 HQ render plan, validate the settings, and queue the job
Probe this timeline for gaps, overlaps, missing media, and source frame ranges
Create a Fusion TextPlus overlay on the selected clip and verify graph connections

Tools 10

app_control writes

Manage Resolve app connection, page switching, project CRUD, databases, and settings.

media_pool writes

Safely import media, manage bins, organize media, normalize metadata, and analyze.

timeline_editing writes

Create and edit timelines, handle clips, tracks, ranges, gaps, and conform operations.

media_analysis read-only

Source-safe analysis of media files, including sync event detection, transcription, visual analysis, and metadata writeback.

review_markers writes

Add, copy, and manage timeline/project markers, generate review reports.

color_grading writes

Inspect node graphs, validate CDLs, manage versions, stills, and color groups.

fusion writes

Create and manage Fusion compositions, tools, and connections.

audio writes

Inspect audio tracks and properties, support voice isolation and auto-sync.

Show 2 more tools

render_deliver writes

Configure render settings, validate formats and codecs, manage render queue.

extension_authoring writes

Helper lifecycle for Fuse, DCTL, and Lua/Python script extensions.

Use cases

List all projects and open one called 'My Film'

Create a timeline from all clips in the current bin

Build a multicam prep timeline

Detect 2-pops or slate claps for sync

Probe timeline for gaps, overlaps, missing media

Build a ProRes 422 HQ render plan

Copy review markers from timeline to clip

Create a Fusion TextPlus overlay

Supported clients

Claude Desktop

Claude Code

Cursor

VS Code

Windsurf

Zed

Continue

Cline

Roo Code

OpenCode

JetBrains IDEs

Listed from the project's documentation, not tested by this site.

Overview

This is a Model Context Protocol (MCP) server that lets AI assistants control DaVinci Resolve Studio through the official Scripting API. It provides full API coverage (349/349 methods) plus guarded workflow helpers for editing, media pool organization, render setup, review markers, grading, Fusion, Fairlight, project lifecycle, extension authoring, and source-safe media analysis. The server offers two modes: Compound (34 tools, default, low context usage) and Full/Granular (341 tools, one tool per API method). An optional offline Advanced server (18 tools) works on .drp/.drt/.drx files and database operations without Resolve running.

Similar servers

Hevy MCP 77 · B

Manage your Hevy workout data from AI assistants via MCP.

★ 511 · Tools 26 Compare with this →

Firecrawl MCP Server 75 · B

Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents

★ 7.6k · Tools 11 Compare with this →

BioMCP 75 · B

One binary. One grammar. Evidence from the biomedical sources you already trust.

★ 654 · Tools 11 Compare with this →

Compartment 75 · B

Encrypted, fully offline long-term memory for AI agents

★ 580 · Tools 14 Compare with this →

Compare with other MCP servers

Source revision ea0a4a446ac6 Data synced 2026-10-13 Read the FMRS scoring method