# Resolve Media Analysis

Media intelligence layer for the DaVinci Resolve MCP.

- Repository: https://github.com/samuelgursky/davinci-resolve-mcp (3887 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-media-analysis -g -a claude-code -y`
Codex: `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-media-analysis -g -a codex -y`
Cursor: `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-media-analysis -g -a cursor -y`
Gemini CLI: `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-media-analysis -g -a gemini-cli -y`

## Description

Media intelligence layer for the DaVinci Resolve MCP. Uses FFprobe, FFmpeg, and optionally Whisper to READ and ANALYZE source media, never modify, transcode, convert, or create derivatives. Provides the MCP with full context of what footage actually is so it can take informed actions within Resolve.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Resolve Media Analysis
This skill wraps the project's canonical media analysis guide with Claude Code-specific integration.

**Read `docs/guides/media-analysis-guide.md` for the complete guide.** Everything below is Claude Code-specific context.

## The First Rule

**Never touch the source.** Your relationship to source media is READ-ONLY. See `docs/guides/media-analysis-guide.md` section "The First Rule: Never Touch the Source" for the full rationale from every post-production department.

## What this build cannot do (check before you offer it)

The scripting API changes per **patch** release, so "Resolve 21" is not a usable
label. Read `resolve_control get_version` → `build.unavailable_on_this_build`
before offering a gated surface; `check_version_support` asks about one named
symbol. Gated in *this* domain, note all of it is Resolve's **own** analysis,
not this repo's:

| Surface | Needs | If absent |
|---|---|---|
| `MediaPoolItem` / `Folder.AnalyzeForIntellisearch` | 21.0 | No IntelliSearch index |
| `Project.ResetIntellisearchAnalysis` | 21.0 | The index cannot be cleared from a script |
| `MediaPoolItem` / `Folder.AnalyzeForSlate` | 21.0 | No automatic slate detection |
| `MediaPoolItem` / `Folder.PerformAudioClassification` / `ClearAudioClassification` | 21.0 | No Resolve-side audio classification |
| `MediaPoolItem` / `Folder.RemoveMotionBlur` | 21.0 | Unavailable |
| `Project.GenerateSpeech` | 21.0 | No AI speech generation |

**This repo's own analysis stack does not depend on any of them.** `analyze_media`
reads frames and audio off disk and runs its own vision/transcription/embedding
tiers, so an older Resolve loses Resolve's AI features, not this pipeline. Say
which one the user is actually missing.

The rest: https://github.com/samuelgursky/davinci-resolve-mcp/blob/HEAD/.agents/skills/resolve-media-analysis/SKILL.md