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.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add samuelgursky/davinci-resolve-mcp --skill docsgit 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/docs)<a href="https://agentmods.dev/skills/samuelgursky/davinci-resolve-mcp/docs"><img src="https://agentmods.dev/badge/skills/samuelgursky/davinci-resolve-mcp/docs/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/docs"><img src="https://agentmods.dev/badge/skills/samuelgursky/davinci-resolve-mcp/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 50 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Excessive Agency · line 326 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 446 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00000 | $0.34212 |
| Opus 5 | $0.00000 | $0.17106 |
| Sonnet 5 | $0.00000 | $0.06842 |
| Haiku 4.5 | $0.00000 | $0.03421 |
Grade B, and why
docs scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
no error anywhere, is usually that. `sudo ln -s "$(command -v python3)" How it starts
The opening of the file, as written. The whole thing — 2,471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DaVinci Resolve MCP Server — AI Skill Reference
This document gives AI assistants the context needed to use the DaVinci Resolve MCP server effectively. It covers the tool landscape, page prerequisites, common workflow patterns, error recovery, and known gotchas.
What This Server Does
The DaVinci Resolve MCP server bridges AI assistants to DaVinci Resolve Studio via its official Scripting API. You can control every aspect of a post-production session — projects, timelines, clips, color grading, Fusion compositions, audio, render queues, and more — through natural language.
DaVinci Resolve must be running with Preferences > General > "External scripting
using" set to Local, or set to Network with RESOLVE_SCRIPT_HOST
configured to the Resolve host IP (use 127.0.0.1 on the same machine). The
server auto-launches Resolve if it is not running, but that first connection can
take up to 60 seconds.
Free edition. Both of those preferences are Studio features; on the free
edition scriptapp("Resolve") refuses a foreign process regardless. A third
transport reaches it — a script run from Workspace ▸ Scripts is handed the
live resolve object on any edition and re-exports it over an authenticated
loopback listener. Install with python scripts/install_resolve_bridge.py and
start it from that menu; once running it is used automatically when external
scripting is unavailable, with no environment variable needed.
DAVINCI_RESOLVE_BRIDGE=1 forces it — the bridge becomes the only transport
tried, so its faults surface directly instead of degrading to another path.
Existing tool call sites work unchanged. Two things to know when diagnosing it:
- On macOS, Resolve finds Python 3 through
PYTHON3HOME, then/usr/local/bin/python3— and nowhere else, so Homebrew/pyenv/uv/conda interpreters simply never appear, with no error. python.org installs work because that installer creates/usr/local/bin/python3; framework-ness itself is not the variable (#143). The sudo-free fix islaunchctl setenv PYTHON3HOME "$(python3 -c 'import sys; print(sys.prefix)')"—launchctl, notexport, because Resolve is GUI-launched and inherits launchd's environment. The installer preflights both routes and ships a Lua canary, which always lists, so "Python not detected" is distinguishable from "wrong folder". The preflight is macOS-only — off macOS Resolve finds Python by other means, and running the check there was a false alarm (#106). Two follow-ups from #182 worth having in hand when a user says the menu is empty despite a setPYTHON3HOME: the prefix needs bothlib/libpython3.X.dylibandbin/python3under that unversioned name (Homebrew framework builds often ship onlypython3.X, so half the check passes on the very interpreter people reach for), andlaunchctl setenvdoes not survive a reboot — a bridge that listed for weeks and then stopped, with no error anywhere, is usually that.sudo ln -s "$(command -v python3)" /usr/local/bin/python3is the persistent alternative. - Windows: both script folders confirmed.
%PROGRAMDATA%(#109) and%APPDATA%(#112) have each been shown serving the bridge on Windows 11 free builds. If a user reports the menu entry missing on Windows, ask whether the Lua canary lists — that separates "wrong folder" from "Python not detected". - A bridge that stops answering while its socket is
LISTENINGis a stale process, not a modal dialog. Before v2.70.3 the Windows bridge could never detect Resolve exiting (os.getppid()does not change there), so it outlived Resolve holding the port and answering with a dead handle — and thebridge_timeoutmessage blamed a modal dialog. On any build, the way out is theshutdownoperation (BridgeClient.bridge_shutdown()); killing the process is the fallback, not the first move. - The control panel connects over the bridge too (fixed in v2.70.2). It runs as a separate process with its own connector, so a panel that reports "Resolve unavailable" while tool calls work is a panel-side bug, not a broken bridge.
- The in-Resolve runtime is a copy taken at install time. After changing the repository, re-run the installer and then ask the running bridge to reload — it re-imports from disk in place, so Resolve does not need restarting.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- authoring/fuse-dctl-authoring.md 12 KB
- authoring/script-plugin-authoring.md 8.3 KB
- authoring/setting-files/README.md 13 KB
- authoring/setting-files/references/category-patterns.md 34 KB
- authoring/setting-files/references/controls.md 13 KB
- authoring/setting-files/references/format.md 24 KB
- authoring/setting-files/references/gotchas.md 14 KB
- authoring/setting-files/references/thumbnails.md 8.0 KB
- authoring/setting-files/templates/MCP Test Blur.setting 985 B
- authoring/setting-files/templates/MCP Test Color Tint.setting 1.8 KB
- authoring/setting-files/templates/MCP Test Cross Dissolve.setting 1.5 KB
- authoring/setting-files/templates/MCP Test Fade Title.setting 2.8 KB
- authoring/setting-files/templates/MCP Test Glow.setting 1.3 KB
- authoring/setting-files/templates/MCP Test Gradient.setting 1.2 KB
- authoring/setting-files/templates/MCP Test Iris.setting 3.5 KB
- authoring/setting-files/templates/MCP Test Lower Third.setting 4.7 KB
- authoring/setting-files/templates/MCP Test Noise.setting 1.6 KB
- authoring/setting-files/templates/MCP Test Solid Color.setting 1.2 KB
- authoring/setting-files/templates/MCP Test Title.setting 2.5 KB
- authoring/setting-files/templates/MCP Test Vignette.setting 2.5 KB
- authoring/setting-files/templates/MCP Test Wipe.setting 2.6 KB
- contributing.md 4.6 KB
- guides/color-decision-guide.md 20 KB
- guides/conforming-an-avid-aaf.md 5.0 KB
- guides/control-panel.md 12 KB
- guides/editorial-decision-guide.md 6.5 KB
- guides/headless-edit-loop.md 12 KB
- guides/media-analysis-guide.md 35 KB
- guides/multicam-setup-guide.md 4.9 KB
- guides/native-drt-authoring.md 13 KB
- images/control-panel/01-overview.png 126 KB
- images/control-panel/02-review-bin-grid.png 126 KB
- images/control-panel/03-clip-detail.png 333 KB
- images/control-panel/04-transcript.png 104 KB
- images/control-panel/05-shot-detail.png 246 KB
- images/control-panel/06-inventory.png 99 KB
- images/control-panel/07-diagnostics-resolve.png 92 KB
- images/control-panel/08-preferences-analysis.png 109 KB
- images/control-panel/09-ai-console.png 146 KB
- images/control-panel/10-history.png 85 KB
- images/control-panel/11-edit-plans.png 71 KB
- install.md 14 KB
- integrations/workflow-integrations.md 5.7 KB
- kernels/audio-fairlight-kernel.md 7.3 KB
- kernels/color-grade-kernel.md 9.6 KB
- kernels/extension-authoring-kernel.md 4.8 KB
- kernels/fusion-composition-kernel.md 7.7 KB
- kernels/media-pool-ingest-kernel.md 9.2 KB
- kernels/project-lifecycle-kernel.md 6.2 KB
- kernels/README.md 5.6 KB
- kernels/render-deliver-kernel.md 9.3 KB
- kernels/review-annotation-kernel.md 4.7 KB
- kernels/timeline-conform-interchange-kernel.md 10 KB
- kernels/timeline-edit-kernel.md 7.8 KB
- notes/codec-plugin-notes.md 5.2 KB
- notes/dctl-notes.md 8.6 KB
- notes/fusion-template-notes.md 5.9 KB
- notes/lut-notes.md 6.3 KB
- notes/openfx-notes.md 5.2 KB
- process/release-process.md 11 KB
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.
- today Changed · +8 lines 505fb6ff46d5
- 2d ago Changed · +18 lines 56c975d3dba3
- 4d ago Changed · +101 lines scan A → B 77243d44fe11
- 5d ago Changed · +53 lines 75a47576b112
- 7d ago Changed 7b397b27b3be
- 9d ago First seen · 2,291 lines · 0 tokens per session scan A a697c8f6da43
docs is a skill published in the GitHub repository samuelgursky/davinci-resolve-mcp (2,508 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 34,212 tokens. A static security scan graded it B with 1 finding (asks for root). 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-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
Comprehensive operational skill specification for Anthropic Claude to automate, script, troubleshoot, and optimize DaVinci Resolve Studio 19, Python Scripting API, Fusion VFX nodes, ACES/DWG color management, and Deliver batch rendering.
davinci-resolve-cli
Use this skill when the user wants to script DaVinci Resolve from the command line — list/open/save projects, batch-import media, queue or wait on render jobs, list timelines/clips, or add/delete timeline markers. Trigger on mentions of DaVinci Resolve, "render this timeline", "import this footage", "tag clips", or…
video-agent-jianying-editor
A video-editing workflow that combines audio, visual files, and subtitles into a draft project for Jianying, the Chinese version of CapCut. It creates a multi-track timeline that can be opened and finished in Jianying.
video-agent-voice
A voice-production workflow that turns a video script into spoken audio and subtitle files. It can also create guidance for someone recording the narration themselves and use storyboard notes about emotion.