MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Color grading and look work in the DaVinci Resolve MCP. An agent skill from samuelgursky/davinci-resolve-mcp.
Install Resolve Color
$ npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-color -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install samuelgursky/davinci-resolve-mcp resolve-color --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/resolve-color .claude/skills/resolve-color && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "resolve-color" agent skill from https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-color into .claude/skills/resolve-color/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-color", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-colorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-color -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install samuelgursky/davinci-resolve-mcp resolve-color --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/resolve-color .agents/skills/resolve-color && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "resolve-color" agent skill from https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-color into .agents/skills/resolve-color/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-color", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-color -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install samuelgursky/davinci-resolve-mcp resolve-color --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/resolve-color .cursor/skills/resolve-color && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "resolve-color" agent skill from https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-color into .cursor/skills/resolve-color/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-color", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/samuelgursky/davinci-resolve-mcp.git --path .agents/skills/resolve-color--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-color -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install samuelgursky/davinci-resolve-mcp resolve-color --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/resolve-color .gemini/skills/resolve-color && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "resolve-color" agent skill from https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-color into .gemini/skills/resolve-color/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-color", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install samuelgursky/davinci-resolve-mcp resolve-colorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-color -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/resolve-color .github/skills/resolve-color && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "resolve-color" agent skill from https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-color into .github/skills/resolve-color/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-color", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-color -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install samuelgursky/davinci-resolve-mcp resolve-color --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/resolve-color .opencode/skills/resolve-color && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "resolve-color" agent skill from https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-color into .opencode/skills/resolve-color/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-color", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
resolve-color- GitHub stars
- 3.5k
- Token cost
- ~1.9k tokens
- SKILL.md length
- 897 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
Color grading and look work in the DaVinci Resolve MCP. An agent skill from samuelgursky/davinci-resolve-mcp.
- Tasks that involve MCP servers
- SKILL.md covers Two servers, one grade, What this build cannot do…, The frame-first rule… and Offline grading / QC catalog…, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Resolve Color is an agent skill from samuelgursky/davinci-resolve-mcp. Color grading and look work in the DaVinci Resolve MCP. Apply when grading, correcting, matching shots, developing looks, or applying/modifying LUTs, CDLs, DRX grades, or copied grades — live in a running Resolve OR offline against .drx/.drp files. Routes to the live Python color tools, the offline advanced grading/QC catalog, and the project's color craft guidance.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol and Python. The repository describes itself as: MCP server integration for DaVinci Resolve Studio. The licence is MIT.
When your agent uses it
- Tasks that involve MCP servers
Example prompts
- “/resolve-color”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 8911bd2. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Resolve Color loads about 1.9k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 897 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from samuelgursky/davinci-resolve-mcp at commit 8911bd2, republished under its MIT licence (© samuelgursky). 897 words, ~1,919 tokens.
Download SKILL.mdSave it as
.claude/skills/resolve-color/SKILL.md (or your agent's skills folder).- name
- resolve-color
- description
- Color grading and look work in the DaVinci Resolve MCP. Apply when grading, correcting, matching shots, developing looks, or applying/modifying LUTs, CDLs, DRX grades, or copied grades — live in a running Resolve OR offline against .drx/.drp files. Routes to the live Python color tools, the offline advanced grading/QC catalog, and the project's color craft guidance.
Resolve Color / Grade
Bridges color craft to this repo's tools. This skill does not duplicate the manuals — it tells you which one to open and the rules that cross both servers.
- Craft / taste —
docs/guides/color-decision-guide.md(project-owned color guidance and API boundaries). The globalcolorist/colorist-assistantskills add colorist philosophy; use them for how to see, not tool mechanics. - Live tool mechanics —
docs/kernels/color-grade-kernel.md(thetimeline_item_colorboundary layer). - Offline grade compute —
resolve-advanced/README.md→ thedrxgrading/QC catalog (the "Advanced (offline) server" section of the color kernel).
Two servers, one grade
| Job | Server | Tools |
|---|---|---|
| Drive a running Resolve | davinci-resolve (Python, live) | timeline_item_color, graph, gallery_stills, color_group |
Compute a grade offline from frames, or read/write .drx/.drp grades with no Resolve open | davinci-resolve-advanced (Node) | drx, drp, project_db, provenance |
Division of labor: the advanced server computes a grade and writes an
apply-ready .drx; applying it is the live server's job
(timeline_item_color.safe_apply_drx). Node never drives Resolve.
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:
| Surface | Needs | If absent |
|---|---|---|
TimelineItem.ResetAllNodeColors | 20.2 | Clear node colors one at a time via the graph node-color setter, or leave them |
An empty unavailable_on_this_build means nothing recorded is missing, not
that everything exists — most of the API has never been version-bisected. A
symbol with no gate returns unknown, which means probe it. Probe with
name in dir(obj), never bare hasattr: on a Resolve object hasattr returns
True for every name, real or invented, so it can only say yes.
The offline drx / project_db routes are not version-gated this way —
they read and write files, so they work regardless of the build attached, and
are the fallback when a live surface turns out to be missing.
The frame-first rule (non-negotiable — see AGENTS.md)
Before applying any grade, look, shot match, LUT, CDL, DRX, or copied grade to a real timeline, inspect representative Resolve-rendered frames (thumbnails, contact sheets, Gallery stills, marker frames, or a scratch-only visual report). Compare bypass/current/after at matched timecodes when the API allows, and restore the prior version/node state after any temporary bypass. Never grade from metadata, graph availability, or a style label alone unless the user explicitly asks for a blind/global pass. Preserve a recoverable grade version and report which frames informed the change. Frames extracted for offline compute go to scratch/analysis locations only — never touch source media (AGENTS.md).
Offline grading / QC catalog (drx actions)
Frame-stats → arithmetic → .drx. All local, deterministic, guarded (they
refuse to fabricate a match rather than emit a silent no-op). Extraction and
apply are the caller's job. Pick by intent:
- Match toward a reference still —
match_to_reference(affine mean/std, skin-line gated, luma-preserving). - Within-camera drift —
level_clips(exposure/WB to a group hero). - Cross-camera skin cohesion —
skin_match(skin-gated; throws on log/wrong-space frames). - B-roll cohesion —
shot_match(gray-world neutralize or hero match). - Known-neutral patch / gray card —
white_balance_match. - Black/white points to a hero —
contrast_normalize. - Saturation cohesion —
saturation_match. Shadow cast —black_balance. - Import ASC CDL (
.cc/.ccc/.cdl) —cdl_io. Copy a Body look —grade_transfer. Attach a.cubeLUT to a node —lut_apply. - Season/host look —
author_look/carry_look. - Read frames —
scope_read(parade/vectorscope/black-balance/clip%),intent_tags(low_key / motivated_warm, to exclude from neutralize),gamut_legal(broadcast-legal, measurement only). - Verify —
verify_grade(intended vs applied → landed/drifted/missing).
Show full SKILL.md (349 more words)Show less
Did the grade damage the image? (media_analysis assess_grade)
verify_grade asks did Resolve apply what I asked. This asks is the result
any good — a grade can land perfectly and still be flat, milky, crunchy or
banded.
media_analysis(action='assess_grade', params={
source_path, graded_path | lut_path, time_seconds, working_space })Deterministic numpy on a decoded frame of the real result (a rendered file,
or the source pushed through the LUT by ffmpeg) — never a simulated transform,
because LUT interpolation and encode rounding are where banding is introduced.
Returns acceptable, flags (each with a remedy), the raw measurements, and a
grade_shift_delta_e2000 magnitude.
- Flags:
flat,milky,washed_out,noisy,clipped,posterized,banding. Read them and reject your own grade rather than shipping the first look that rendered. - Display-referred only. ACEScct / S-Log3 / LogC are refused, not converted — the right transform depends on camera and project colour management, which a frame cannot tell you. Convert first, then re-run.
visionin the result says whether a paid second opinion is warranted. Content-dependent flags (bandingon a real sky gradient, a deliberatewashed_out) escalate; unambiguous damage does not. A clean grade costs zero tokens.
Cross-server gotchas that bite
- Grade value space.
drxgenerate/mergedefault tospace:'ui'(Resolve PANEL units; saturation 0–100, neutral 50). Passspace:'drx'only for raw internal floats. Decoded values are ground truth only for the calibrated set — check thevalueFidelitymarker (resolve-advanced/vendor/drx-parameters/CALIBRATION-STATUS.md). - Hue-axis curves. Naive
[0,1]point lists are auto-canonicalized into the verified bezier cage. If a result carries awarningsarray, the curve went through raw and will render FLAT — surface it, do not ship silently. - Apply targeting.
safe_apply_drxdefaults to video track 1 / item 0 — always passtrack_type/track_index/item_indexexplicitly, and grab a still/.drxbackup first (it does not snapshot).ApplyGradeFromDRXreplaces the graph — no append mode. - Relayout ("Cleanup Node Graph," no UI API). Single clip, live: grab still →
drx(action="relayout")→graph.reset_all_grades→safe_apply_drxwith explicit indices (a same-structure apply keeps the OLD layout — the reset is required). Whole project, offline:project_db(action="relayout_node_graphs"). - Guards are load-bearing. A thrown "refused" error usually means wrong input
space, log-encoded frames, or missing media — read it before retrying. The
grading catalog needs
sharp; call the advancedcapabilitiestool for live status + install hints.
© samuelgursky, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/resolve-color of samuelgursky/davinci-resolve-mcp.
Open the folder on GitHubat commit 8911bd2
Compare with similar skills
Resolve Color next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Resolve Color this skillsamuelgursky/davinci-resolve-mcp | 3.5k | — | ~1.9k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MemPalace Setup and OperationMemPalace/mempalace | 60k | — | ~2.2k | Automated safety check: Pass | MIT | |
| FastmcpTommy-yw/RunbookHermes | 546 | 3 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Fastmcp Client CLIPrefectHQ/fastmcp | 28k | — | ~823 | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
MemPalace Setup and Operation
MemPalace/mempalace
Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.
Fastmcp
Tommy-yw/RunbookHermes
Build, test, inspect, install, and deploy MCP servers with FastMCP in Python.
Fastmcp Client CLI
PrefectHQ/fastmcp
Query and invoke tools on MCP servers using fastmcp list and fastmcp call.
Migrate To Archestra
archestra-ai/archestra
Migrate an existing agentic PoC/pilot (Claude Code project files, MCP configs, hooks, local tools, openclaw config, or similar hand-rolled setup artifacts) into an Archestra instance.
More from samuelgursky/davinci-resolve-mcp
All 14 skills in this repoResolve MCP
samuelgursky/davinci-resolve-mcp
Orientation and index for DaVinci Resolve MCP work — grading, editing, conforming, delivery, media analysis, and .drp/.drt/.drx file work, live in a running Resolve or offline with none open.
Resolve Rough Cut
samuelgursky/davinci-resolve-mcp
Assembling a short-form social rough cut from raw behind-the-scenes or vlog footage in the DaVinci Resolve MCP.
House Style
samuelgursky/davinci-resolve-mcp
The editorial and finishing preferences this project's work is judged against — cut rhythm, shot selection, delivery conventions, and the corrections that have already been given.
Resolve Audio
samuelgursky/davinci-resolve-mcp
Audio and Fairlight work in the DaVinci Resolve MCP. An agent skill from samuelgursky/davinci-resolve-mcp.
Resolve Conform
samuelgursky/davinci-resolve-mcp
Conforming, relinking, and finishing prep in the DaVinci Resolve MCP.
Resolve Delivery
samuelgursky/davinci-resolve-mcp
Delivery, rendering, and deliverable QC in the DaVinci Resolve MCP.
Related
Works with
Categories
Questions about Resolve Color
What does Resolve Color do?
Color grading and look work in the DaVinci Resolve MCP. An agent skill from samuelgursky/davinci-resolve-mcp. Resolve Color is an agent skill from samuelgursky/davinci-resolve-mcp. Color grading and look work in the DaVinci Resolve MCP.
When should I use Resolve Color?
Resolve Color fits situations like: tasks that involve MCP servers.
How do I install Resolve Color in Claude Code?
Run `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-color -a claude-code`. Or copy the skill folder (.agents/skills/resolve-color in samuelgursky/davinci-resolve-mcp) into .claude/skills/resolve-color in your project. Claude Code loads it when a task matches its description.
How do I install Resolve Color in Codex?
Run `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-color -a codex`. Or copy the skill folder (.agents/skills/resolve-color in samuelgursky/davinci-resolve-mcp) into .agents/skills/resolve-color in your project. Codex loads it when a task matches its description.
Can I use Resolve Color in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-color -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/resolve-color, .gemini/skills/resolve-color, .github/skills/resolve-color and .opencode/skills/resolve-color in your project.
What does Resolve Color need to run?
SKILL.md names no scripts, command-line tools or credentials: Resolve Color is instructions for the agent only. Our summary lists: Python 3.
Does Resolve Color access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Resolve Color safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Resolve Color use?
Resolve Color is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Resolve Color use?
About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Resolve Color?
Skills that share tags, products or a category with Resolve Color: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MemPalace Setup and Operation (MemPalace/mempalace, 60k stars) and Fastmcp (Tommy-yw/RunbookHermes, 546 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Resolve Color?
samuelgursky (a GitHub user) maintains it in samuelgursky/davinci-resolve-mcp, which has 3,461 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 10, 2026.
Source: samuelgursky/davinci-resolve-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.