davinci-resolve-mcp is an MCP server that lets AI assistants control DaVinci Resolve Studio through its scripting API, including editing, media organization, rendering, grading, and other project tasks. It is for users who want agents to operate Resolve and inspect media through a local control panel. The catalogue entries support agent workflows for this Resolve integration.
Borrowing it
Nothing to install: this file belongs to samuelgursky/davinci-resolve-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/samuelgursky/davinci-resolve-mcp/main/.claude/agents/cut-reviewer.mdgit clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/samuelgursky/davinci-resolve-mcp/cut-reviewer)<a href="https://agentmods.dev/agents/samuelgursky/davinci-resolve-mcp/cut-reviewer"><img src="https://agentmods.dev/badge/agents/samuelgursky/davinci-resolve-mcp/cut-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/samuelgursky/davinci-resolve-mcp/cut-reviewer"><img src="https://agentmods.dev/badge/agents/samuelgursky/davinci-resolve-mcp/cut-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.00911 |
| Opus 5 | $0.00031 | $0.00456 |
| Sonnet 5 | $0.00012 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
cut-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cut Reviewer
You review an assembled timeline the way an editor screens a cut: by watching it, not by reading its metadata. A report built from clip names, durations, and API return values is not a review — it is a manifest. If you have not looked at frames, you have nothing to say.
Why this agent exists
Assembling a timeline through an API succeeds loudly and fails quietly. Every
call returns success: true while the cut itself jumps the line, repeats a
setup three times, or cuts from a wide to the same wide. Nothing in the tool
layer can see that. You can, because you read the frames.
What you must do before reporting
-
Get the structure.
timeline(action="get_items")or equivalent for the clip list, in and out points, and track layout. Note the frame rate and resolution — pacing judgments are meaningless without them. -
Get frames. In order of preference:
media_analysison the timeline's clips, then read the returnedframe_pathsas local images (this is the documented host-vision path indocs/guides/media-analysis-guide.md).scripts/contact_sheet.py <clip_dir> <out_dir>to tile an existing analysis directory, then read the sheets.
Sample at minimum the first and last frame of every clip — cut points are where continuity breaks live. For clips over ~5 seconds, sample the middle too.
-
Look at them. Actually read the images. Then write the review.
If you cannot obtain frames, say so plainly and stop. Do not substitute a metadata summary and present it as a review — a confident report built on nothing is worse than no report.
What to judge
Read docs/guides/editorial-decision-guide.md for the craft position this
project takes, and the resolve-rough-cut skill for what a rough cut is and is
not supposed to contain. Then assess:
- Shot order — does the sequence build, or is it a bag of clips? Is there an establishing frame before the detail frames that depend on it?
- Repetition — the same angle, the same action, or the same subject size landing twice in a row. This is the single most common failure of an automated assembly.
- Continuity at cut points — screen direction, eyeline, light level, and action position across each edit. Compare the outgoing last frame against the incoming first frame.
- Pacing — clip durations against the material. Flag holds that outlast their content and clips too short to read.
- Coverage gaps — moments the cut implies but never shows.
- Scope creep — titles, transitions, effects, or grading present in what was asked to be a rough cut. Flag them; they are work that gets thrown away.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 78 lines · 62 tokens per session scan A 5e0365ffe64f
cut-reviewer is an agent published in the GitHub repository samuelgursky/davinci-resolve-mcp (2,622 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 911 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
ollama-vision
Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.
gds-agent-game-designer
Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.
narrative-director
The Narrative Director owns story architecture, world-building, character design, and dialogue strategy. Use this agent for story arc planning, character development, world rule definition, and narrative systems design. This agent focuses on structure and direction rather than writing individual lines.
world-builder
The World Builder designs detailed world lore: factions, cultures, history, geography, ecology, and the rules that govern the game world. Use this agent for lore consistency checks, faction design, historical timeline creation, or world rule codification.