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-delivery/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-delivery)<a href="https://agentmods.dev/skills/samuelgursky/davinci-resolve-mcp/resolve-delivery"><img src="https://agentmods.dev/badge/skills/samuelgursky/davinci-resolve-mcp/resolve-delivery/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-delivery"><img src="https://agentmods.dev/badge/skills/samuelgursky/davinci-resolve-mcp/resolve-delivery.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 | $0.00122 | $0.02100 |
| Opus 5 | $0.00061 | $0.01050 |
| Sonnet 5 | $0.00024 | $0.00420 |
| Haiku 4.5 | $0.00012 | $0.00210 |
Grade A, and why
resolve-delivery 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve Delivery / Deliverable QC
Bridges delivery craft to this repo's tools.
- Craft / specs — the global
deliverables-knowledge,post-supervisor, andquality-control/qc-domainskills (distributor specs, mastering, QC discipline). Use for what the spec should be, not tool mechanics. - Live tool mechanics —
docs/kernels/render-deliver-kernel.md(therenderplanning/validation boundary + Quick Export). - Offline deliverable QC —
resolve-advanced/README.md→deliverable,media,provenance.
Two servers
| Job | Server | Tools |
|---|---|---|
| Plan / validate / run renders in a running Resolve | davinci-resolve (Python, live) |
render, render_presets |
| QC a finished render vs spec, verify ingest, build manifests/provenance with no Resolve open | davinci-resolve-advanced (Node) |
deliverable, media, provenance |
Delivery targets (the short path)
Named render intents. list_delivery_targets → prepare_delivery_job(target, target_dir). Ask for prores422hq_master, dnxhr_hqx_master, h264_1080p_web,
or an alias (youtube, tiktok, avid, stems). One definition emits BOTH the
Resolve render settings and the deliverable_qc spec, so the returned qc_spec
is what you QC the finished file against — do not hand-write a second spec.
-
Format/codec resolve against the live matrix. A target this machine or license cannot render fails with the available lists; it never silently substitutes. Use
check_availability: trueto see what this install supports. -
Image-sequence targets return
qc_spec: null—deliverable_qcprobes one file, a sequence is many. That is expected, not a gap. -
Bitrate is deliberately unset (Resolve has no bitrate key). Pin quality yourself via
settingsif a spec demands it. -
Programme loudness is a separate projection. A target names a standard via
overrides: {loudness_standard: "ebu_r128"};resolve_delivery_targetthen returns aloudness_targetalongsideqc_spec. Handloudness_target.targetto advancedloudness_qc.render(action='list_loudness_standards')lists the five named contracts (web,podcast,ebu_r128,atsc_a85,ott_dialogue_gated) — cite one, never invent the numbers. -
No shipped target names a loudness standard by default: a ProRes master has no inherent programme loudness and a broadcast handoff depends on territory. A
loudness_notetells you when none is pinned. -
Dialogue-gated standards emit no gradeable
integrated.loudness_qcmeasures full-programme; grading a dialogue-gated figure against that means nothing. The number rides inmetafor a properly gated meter and only true peak is asserted. This is deliberate, not a missing field.
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 a14e74224363
- 12d ago First seen · 139 lines · 122 tokens per session scan A 9a31249ccff8
resolve-delivery is a skill published in the GitHub repository samuelgursky/davinci-resolve-mcp (2,701 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 2,100 once invoked, about $0.0006 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.