AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Vision / Multimodal/
davinci-resolve-mcp
davinci-resolve-mcp logo

davinci-resolve-mcp

Active·★ 3.7k·MIT·Updated 2026-10-19

This MCP server connects AI assistants such as Claude, Cursor and Windsurf to DaVinci Resolve and exposes the application's scripting API as tools, so you can drive post-production tasks in natural language. The README claims 324 of 324 non-deprecated API methods are covered. By default the server groups them into 26 compound tools selected by an action parameter, which keeps the model's context small; a full mode offers 342 granular tools, one per method. The timeline_item tool has dedicated actions for retiming, transforms, cropping, compositing, audio and keyframes.

Requirements are specific: DaVinci Resolve Studio 18.5 or newer (the README says the free edition does not support external scripting), Python 3.10 to 3.12 recommended, and Resolve running with external scripting set to Local in the preferences. A single `python install.py` finds Resolve, creates a virtual environment and writes the config for the MCP client you choose; ten clients are listed, from Claude Desktop and Claude Code to Cursor, VS Code, Zed and JetBrains. The README reports live testing against Resolve 19.1.3 Studio on macOS, 319 of 324 methods passing, with the five untested ones needing cloud projects or Dolby Vision content.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-18.

License
MIT
Latest release
v4.14.1 · 2026-10-18
Last commit
2026-10-18
Contributors
55
Forks
433
Open issues and PRs
3
First published
2025-03-18

Source: GitHub, npm and PyPI public APIs.

#DaVinci Resolve#Scripting API#AI Assistant#Model Context Protocol#Video Editing#Post-Production#Python#Workflow Automation
$ Install
$ git clone https://github.com/samuelgursky/davinci-resolve-mcp.git && cd davinci-resolve-mcp && python install.py
↗ Visit site★ GitHub
01

Features

01Complete coverage of the DaVinci Resolve Scripting API (324/324 methods).
02Offers both a 26-tool compound server for efficiency and a 342-tool granular server for power users.
03Universal installer supports macOS, Windows, Linux, and auto-configures 9 MCP clients.
04Dedicated timeline_item actions including retime, transform, crop, composite, audio, and keyframes with validation.
05Features lazy connection to DaVinci Resolve, ensuring the server starts instantly and connects only when needed.
02

Why choose it

+Very broad coverage of the Resolve scripting API, with a per-method test status table in the README
+Compound mode keeps tool count (and context use) low; full mode is available for power users
+One installer configures ten MCP clients across macOS, Windows and Linux
+Server starts instantly and connects to Resolve lazily on the first tool call
03

Trade-offs

!Needs the paid DaVinci Resolve Studio; the free edition cannot be scripted externally
!Python 3.13 and newer may be incompatible with Resolve's scripting library, per the README
!The test results are the author's own, run on one Resolve version and one OS
!Some operations are destructive (the test plan includes delete and quit calls), so work on a copy of important projects
05

Maintenance check

ActiveChecked: 2026-10-17
Last commit
2026-10-17
Commits, last 90 days
100+
Releases, last 90 days
30
Latest release
v4.13.7 (2026-10-17)
Open issues
1
Recent issues with at least one comment
7/7
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 56, 104, 30, 31, 18, 148, 87, 85, 15, 8, 27, 43

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #290 resource hungry - why not us the GPU?1 comments · 2026-10-15

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You use DaVinci Resolve for professional editing, grading, or audio post-production and want AI assistants to execute operations via the official Scripting API.
  • You want to automate timeline generation, color grading presets, marker creation, and media pool metadata ingestion with natural language.
Look elsewhere if
  • You work in Adobe Premiere Pro or Final Cut Pro (this MCP is tightly coupled to DaVinci Resolve's Python scripting runtime).
  • You want a standalone, lightweight open-source video editor without installing DaVinci's multi-gigabyte suite (choose Concat).
06

How it differs

Concat logovs Concat★ 10.5k

davinci-resolve-mcp bridges LLMs into the professional DaVinci Resolve NLE; Concat is an independent lightweight open-source video editor with built-in AI.

Full comparison →
blender-mcp logovs blender-mcp★ 31.9k

Both bridge AI into creative desktop software: DaVinci Resolve MCP controls video editing and grading; Blender-MCP controls 3D modeling and scenes.

Full comparison →
07

Compatibility

DaVinci Resolve
Software
Verified via docs
Python
Runtime
Verified via docs
MacOS
OS
Verified via docs
Windows
OS
Verified via docs
Linux
OS
Verified via docs
Claude
AI Client
Verified via docs
08

Quick start

1
$ git clone https://github.com/samuelgursky/davinci-resolve-mcp.git
2
$ cd davinci-resolve-mcp
3
$ python install.py
09

Use cases

↳Control DaVinci Resolve post-production workflows through natural language using AI assistants.
↳Automate project management tasks such as creating, loading, and saving projects.
↳Streamline timeline operations, including creating timelines, adding clips, and setting markers.
↳Automate rendering and export processes for various formats like ProRes or EDL.
↳Perform advanced editing actions like creating Fusion compositions or grabbing stills.
10

Alternatives

⚡Top VS:
VSblender-mcp★31.9k→VSConcat★10.5k→VSdavinci-mcp-professional★25→VSblenderwright★175→
blender-mcp logo
blender-mcp★ 31.9k
Community plugin to control Blender 3D with any LLM of your choice
VSCompare→
Concat logo
Concat★ 10.5k
The truly free, and open-source cross-platform CapCut replacement (supports MCPs).
VSCompare→
davinci-mcp-professional logo
davinci-mcp-professional★ 25
An enterprise-grade MCP server that exposes the full functionality of DaVinci Resolve and DaVinci Resolve Studio (through version 20) to either Claude Desktop or Cursor MCP clients. Fully configured and tested as a Claude Desktop Extension making installation as easy as clicking a button. Supports both Windows and Macintosh.
VSCompare→
blenderwright logo
blenderwright★ 175
MCP server for Blender. 191 tools for modelling, materials, rendering and more, driven by Claude, Cursor, Codex, Ollama, llama.cpp, or any MCP client.
VSCompare→
cml-mcp logo
cml-mcp★ 76
A Model Context Protocol (MCP) Server for Cisco Modeling Labs (CML)
VSCompare→
mcp-blender logo
mcp-blender★ 29
The most comprehensive MCP server for Blender — 218 tools for 3D modeling, AI generation, MSFS content creation, and more
VSCompare→
aws-mcp-server logo
aws-mcp-server★ 186
A lightweight service that enables AI assistants to execute AWS CLI commands (in safe containerized environment) through the Model Context Protocol (MCP). Bridges Claude, Cursor, and other MCP-aware AI tools with AWS CLI for enhanced cloud infrastructure management.
VSCompare→
freecad-addon-robust-mcp-server logo
freecad-addon-robust-mcp-server★ 258
The FreeCAD Robust MCP server and MCP Bridge Workbench/Addon
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06How it differs07Compatibility08Quick start09Use cases10Alternatives
samuelgursky /
davinci-resolve-mcp
↗

MCP server covering the full DaVinci Resolve scripting API

3.7k433MIT
Last commit3d ago
StatusActive
CategoryVision / Multimodal
Contributors55
Latest releasev4.14.1
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.