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/.agents/skills/resolve-audio/SKILL.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/skills/samuelgursky/davinci-resolve-mcp/resolve-audio)<a href="https://agentmods.dev/skills/samuelgursky/davinci-resolve-mcp/resolve-audio"><img src="https://agentmods.dev/badge/skills/samuelgursky/davinci-resolve-mcp/resolve-audio/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/skills/samuelgursky/davinci-resolve-mcp/resolve-audio"><img src="https://agentmods.dev/badge/skills/samuelgursky/davinci-resolve-mcp/resolve-audio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00086 | $0.01326 |
| Opus 5 | $0.00043 | $0.00663 |
| Sonnet 5 | $0.00017 | $0.00265 |
| Haiku 4.5 | $0.00009 | $0.00133 |
Grade A, and why
resolve-audio 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 10d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve Audio / Fairlight
Thin router; depth stays in the kernel.
- Live tool mechanics —
docs/kernels/audio-fairlight-kernel.md(thetimelineaudio/Fairlight boundary). - Offline planning + bus routing —
resolve-advanced/README.md→audio_plan,fairlight,audio.
Rough mix before anything else
If the ask is "make this sound balanced" rather than "route these buses", start with
media_analysis mix_plan (Python server, no Resolve needed). Give it the dialogue stems
and it derives the dialogue-normalisation gain, the music-bed level under it, and ducking
windows from the dialogue's own silence — then renders a premix and measures it, so
what you report is the loudness achieved rather than the gain arithmetic.
dry_run defaults to true: show the gains and the window count first. On a
full-programme standard (ebu_r128, web) a measured programme trim lands the whole mix
on target; on ott_dialogue_gated it deliberately does not trim, because dialogue is the
figure being graded. Flags (loudness_off_target, true_peak_over, clipped) come back
with remedies and are never auto-corrected — report them, do not paper over them.
Two servers — plan/measure offline, apply live
| Job | Server | Tools |
|---|---|---|
| Audio on a running timeline | davinci-resolve (Python, live) |
timeline (`probe_audio_item |
| Plan tracks / route buses / edit audio files with no Resolve open | davinci-resolve-advanced (Node) |
audio_plan, fairlight, audio |
Offline
audio_plan(pure Node) —list_templates,select_template,track_plan,analyze_coverage,check_loudness(R128 −23 / ATSC −24 / streaming −14 targets). Plan the layout before building it live.fairlight— bus routing has no scripting API; it patches theFLStudioModelBAblob.read_buses_from_blob(offline);read_buses_from_db,expand_buses,export_template/import_template,backup,restore(DB path — needsbetter-sqlite3; project CLOSED + quit/relaunch like other DB patches).audio— offline ffmpeg:split(silence/TC/intervals),trim,convert(needs ffmpeg on PATH — GPL, not bundled). Align/loudness-measure not yet vendored.
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.
- 10d ago Changed · -1 lines 1017d938aa28
- 12d ago First seen · 88 lines · 86 tokens per session scan A 2bcd39a47b62
resolve-audio is a skill published in the GitHub repository samuelgursky/davinci-resolve-mcp (2,701 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 1,326 once invoked, about $0.0004 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 skills, from other repositories
cyxj-blog-pub
A publishing workflow for adding a finished article to an Astro blog, a website built with the Astro framework.
cyxj-transcript
A workflow that turns a video or audio transcript into a structured article draft in Obsidian Markdown.
cyxj-video-cover
A generator for making 16:9 video-cover background scenes without text, letters, numbers, logos, or watermarks.
skill
Skill "skill" from Mun1to/vidorq, covering vidorq skill — edición por ia (v1), flujo, uso, 1) transcribir (word-level, local) and 3) renderizar.
davinci-resolve
Automate DaVinci Resolve media and timelines with its scripting API, build Fusion workflows, and configure render jobs.
cyxj-jingxuan
A writing assistant for applying to have a finished video selected for 抖音精选, a curated feature on the Douyin video platform. It reads the video's actual subtitles or transcript and writes a 150–250 character Chinese application in four sections.