DEV.co
MCP Servers · samuelgursky

davinci-resolve-mcp

DaVinci Resolve MCP Server is a Python integration that lets AI assistants control the DaVinci Resolve video editing software through its official scripting API. It bundles 34 tools (or 341 granular methods) for timeline editing, media pool management, color grading, and project lifecycle tasks, plus an optional Node.js-based advanced server for offline file editing and analysis.

Source: GitHub — github.com/samuelgursky/davinci-resolve-mcp
1.4k
GitHub stars
167
Forks
Python
Primary language
MIT
License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

FieldValue
Repositorysamuelgursky/davinci-resolve-mcp
Ownersamuelgursky
Primary languagePython
LicenseMIT — OSI-approved
Stars1.4k
Forks167
Open issues0
Latest releasev2.60.0 (2026-07-06)
Last updated2026-07-06
Sourcehttps://github.com/samuelgursky/davinci-resolve-mcp

What davinci-resolve-mcp is

This MCP server implements the Model Context Protocol to expose DaVinci Resolve's Python scripting API as callable tools for LLM agents. It supports two modes: compound (34 tools grouping related operations) and full/granular (one tool per API method). An optional advanced server (Node.js/JS) reads and edits Resolve project files (.drp/.drt/.drx) offline without a live Resolve instance, adding 18 specialized tools for grading, media analysis, and pipeline automation.

Quickstart

Get the davinci-resolve-mcp source

Clone the repository and explore it locally.

terminalbash
git clone https://github.com/samuelgursky/davinci-resolve-mcp.gitcd davinci-resolve-mcp# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

AI-assisted video editing automation

Agents can automate timeline assembly, media pool organization, shot selection, and project structure tasks via natural language commands integrated into IDE code completions (Claude Desktop, Cursor, VS Code, Zed, JetBrains).

Batch grading and color pipeline automation

Automate color correction workflows, apply LUT chains, perform quality checks, and manage season-look carry-over across episodes using the advanced offline server tools for deterministic, repeatable grading without manual Resolve UI interaction.

Post-production pipeline tooling

Build conform QC, editorial integrity checks, deliverable compliance validation, and provenance tracking through the offline server's DB-level project tools; integrate into CI/CD-style post workflows with source-safe media analysis and frame extraction.

Implementation considerations

  • Resolve 18.5+ with Studio edition and Python 3.10+ required; prefer clean git checkout for safe auto-update. Live server checks GitHub for updates on best-effort basis (throttled, non-blocking).
  • Two modes available: compound (34 tools, recommended for most agents) and full/granular (341 tools, for power users); choose based on context budget and token usage needs.
  • Optional Node.js advanced server requires ffmpeg and sharp/better-sqlite3 for full offline features; capabilities tool reports live status and install hints. Pure JS/MIT core with optional tool dependencies.
  • Local browser control panel for state inspection, source-safe media analysis, and inline report editing; runs from repo root via `venv/bin/python -m src.control_panel`.
  • AI agents must use `venv/bin/python -m src.control_panel` or `src/server.py` unless Python environment is pre-activated; installer handles detection of Resolve paths and IDE configuration (Claude, Cursor, VS Code, etc.).

When to avoid it — and what to weigh

  • Real-time live-action recording or ingest — This is a control/automation layer for existing Resolve projects and media; it does not handle camera ingest, real-time capture, or live-stream integration.
  • Air-gapped or offline-only Resolve instances — The live MCP server requires Resolve Studio running locally with scripting enabled. The offline advanced server is optional; without it, no live Resolve means no functionality.
  • Cross-platform Resolve Free/Community edition — The server targets DaVinci Resolve Studio 18.5+ and its scripting API; Resolve Free does not include the Python scripting layer, so this tool will not work.
  • Unattended, headless operation without manual setup — Requires Resolve Studio running, Preferences scripting enabled, and a Python environment; no headless daemon mode. Bradford Post Assistant (closed beta) may address this in the future.

License & commercial use

MIT License. Permissive OSI-approved license allowing commercial use, modification, and distribution. No attribution required, but notice and license text should accompany redistribution.

MIT is a permissive OSI license that explicitly permits commercial use, including proprietary derivative products, without licensing fees or restrictions. However, any derivative work must retain the MIT notice. No commercial support, warranty, or SLA is stated; review maintainer's commercial services (Bradford Post Assistant is closed beta, separate product) separately.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

SignalAssessment
MaintenanceActive
DocumentationStrong
License clarityClear
Deployment complexityLow
DEV.co fitGood
Assessment confidenceHigh
Security considerations

Live server requires Resolve Studio with local scripting enabled; communication is local IPC/file-based. Advanced server reads and modifies Resolve project files (.drp/.drt/.drx) offline; validate file integrity and ownership before processing untrusted project files. No external network calls documented for core MCP tools (update checks are optional, best-effort). Bradford Post Assistant (closed beta) claims encrypted on-device memory; review separately. Always run Resolve and MCP on trusted workstations; grade files and media are local and unencrypted at rest.

Alternatives to consider

DaVinci Resolve's built-in Python API (direct scripting)

Offers direct API access without MCP abstraction; requires custom script development. Less integrated with AI agents and IDEs; suitable for single-purpose automation scripts, not conversational AI guidance.

Blackmagic Fusion Scripting API

Focuses on Fusion node-based compositing; does not cover color grading, Fairlight audio, or timeline editing in Resolve. Requires manual script authoring; not MCP-exposed or LLM-friendly.

Third-party Resolve plugins and extensions

Ecosystem of UI plugins (e.g., ScriptClip, custom panels) for specific tasks; each requires separate licensing, installation, and maintenance. Less flexible for custom AI-driven workflows; not designed for LLM agent control.

Software development agency

Build on davinci-resolve-mcp with DEV.co software developers

Use DaVinci Resolve MCP to let AI agents handle timeline assembly, color grading, media management, and compliance checks. Get started with npm, connect to Claude Desktop or your IDE, and streamline your workflow.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

Related on DEV.co

Explore the category and the services that help you build with it.

davinci-resolve-mcp FAQ

Does this work with DaVinci Resolve Free?
No. Resolve Free does not include the Python scripting layer. Studio edition 18.5+ is required.
Can I run this headless without a GUI?
The live MCP server requires Resolve Studio running with scripting enabled; no headless daemon mode is documented. The optional advanced offline server (Node.js) can read/edit project files without Resolve running, but that is a separate, specialized tool.
What is the difference between the compound and full server modes?
Compound mode (default, 34 tools) groups related Resolve operations behind action parameters to minimize context/token usage. Full mode (341 granular tools) exposes one tool per API method; use when you need fine-grained control and have ample context budget.
Is there commercial support or a service?
The open-source servers are community-maintained under MIT. Bradford Post Assistant, a closed-beta managed desktop application, is under active development by the maintainers as a commercial product; request access at bradfordoperations.com.

Software development & web development with DEV.co

DEV.co is a software development agency delivering custom software development services to companies building on open source. Our software developers and web developers design, integrate, and ship production systems — spanning web development, APIs, AI, data, and cloud. If davinci-resolve-mcp is part of your mcp servers roadmap, our team can implement, customize, migrate, and maintain it.

Integrate AI Automation into Your Post-Production Pipeline

Use DaVinci Resolve MCP to let AI agents handle timeline assembly, color grading, media management, and compliance checks. Get started with npm, connect to Claude Desktop or your IDE, and streamline your workflow.