mcp-da-vinci: Instructions file for Claude Code

CLAUDE.md

mcp-da-vinci CLAUDE.md is an instructions file for Claude Code from AmreetKumarkhuntia/mcp-da-vinci. It costs 1,349 tokens per session, scanned A, original, MIT.

A set of instructions for using a local MCP server that connects an AI coding agent to DaVinci Resolve, a video-editing and motion-graphics application. It covers the server structure, Windows and WSL setup, and Fusion frame handling.

In plain words
What is it for?
Running Resolve tools, inspecting compositions, setting the playhead, grabbing frames, and building motion-graphics workflows with Fusion.
Why use it?
It prevents common mistakes when controlling Resolve from a Linux-like environment, especially mixing timeline frames with Fusion composition frames.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is AmreetKumarkhuntia/mcp-da-vinci's own configuration. It tells Claude Code how to work on mcp-da-vinci itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-da-vinci configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AmreetKumarkhuntia/mcp-da-vinci. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/AmreetKumarkhuntia/mcp-da-vinci/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AmreetKumarkhuntia/mcp-da-vinci

Made for: Claude Code.

Wrote 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.

agentmods badge for mcp-da-vinci CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/amreetkumarkhuntia/mcp-da-vinci/claude-md/github.svg)](https://agentmods.dev/instructions/amreetkumarkhuntia/mcp-da-vinci/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/amreetkumarkhuntia/mcp-da-vinci/claude-md"><img src="https://agentmods.dev/badge/instructions/amreetkumarkhuntia/mcp-da-vinci/claude-md/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.

agentmods 80×15 button for mcp-da-vinci CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/amreetkumarkhuntia/mcp-da-vinci/claude-md"><img src="https://agentmods.dev/badge/instructions/amreetkumarkhuntia/mcp-da-vinci/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,349 This file is loaded in full into every session.
When invoked 1,349 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01349 $0.01349
Opus 5 $0.00674 $0.00674
Sonnet 5 $0.00270 $0.00270
Haiku 4.5 $0.00135 $0.00135

Measured 11d ago against content hash 0e4701dfe165, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-da-vinci CLAUDE.md 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.

CLAUDE.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

MCP server exposing DaVinci Resolve's scripting API. Everything here runs under Windows Python (python.exe from WSL) because fusionscript.dll is a Windows binary — never use a WSL python for server, CLI, or one-off probes.

Architecture

server.py imports resolve/app.py's shared FastMCP instance, then the tools/* modules, whose @mcp.tool() decorators register everything. resolve/connection.py owns the Resolve handle (get_resolve(), cached) plus comp/clip helpers. Dev loop: python.exe cli.py <tool> --arg value (one-shot) or python.exe console.py (warm REPL, slash commands). Windows paths everywhere a file reaches Resolve.

Fusion: the two time domains

  • Timeline frames are absolute: get_timeline_info.start_frame is e.g. 86400 (= 01:00:00:00 @ 24 fps). set_playhead --frame and grab_frame --frame use these.
  • Fusion keyframes are comp-relative: usually 0..duration-1. Always call fusion_get_comp_info first; it returns render_start/render_end (valid key range) and the mapping: timeline_frame = timeline_start_frame + (comp_frame - global_start).

The motion-graphics loop

  1. fusion_get_comp_info — frame range + timeline mapping.
  2. fusion_get_node --name X --filter <substring> — discover input ids + datatypes (always filter on big nodes; TextPlus has ~300 inputs).
  3. Set: fusion_set_value / fusion_set_text / fusion_set_point (statics), fusion_set_keyframes (whole curve incl. easing), fusion_set_point_keyframe (motion paths).
  4. Verify numerically: fusion_sample_input --frames a --frames b ....
  5. Verify visually: grab_frame --frame <timeline_frame> — you get the rendered image.
  6. Adjust and repeat.

Verified API facts (probed live on Resolve 19.1.3, don't rediscover)

  • Script-created keyframes interpolate linearly by default. Easing comes from BezierSpline handle tables — fusion_set_keyframes --interpolation handles this; the spline Flags route (Linear/StepIn) does NOT work over remote scripting.
  • A clip's comp is scriptable only while loaded (clip under the playhead on the topmost visible track). Other clips' comp handles answer with an empty tool list; get_comp raises an actionable error for this. Fix: set_playhead onto the clip.
  • Modifier registry ids: PerturbNumber / PerturbPoint (UI "Perturb"), Shake, StyledTextFollower (UI "Follower"), XYPath, Path. fusion_add_modifier aliases Perturb/Follower to the right ids. Modifiers appear in fusion_list_nodes and are addressable by name like any node.
  • SetCurrentTimecode is rejected on the fusion/media pages (grab_frame and set_playhead know this; grab_frame does the page dance itself).
  • GrabStill works from any page; ExportStills also emits a .drx sidecar.
  • Common input ids: Blur strength = XBlurSize; Transform = Center/Size/Angle; Merge opacity = Blend; TextPlus text = StyledText, size = Size, color = Red1/Green1/Blue1/Alpha1.

Read the full file on GitHub · 84 lines

Changes

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.

  1. 11d ago First seen · 84 lines · 1,349 tokens per session scan A 0e4701dfe165

Subscribe to this mod's changes

mcp-da-vinci CLAUDE.md is an instructions file published in the GitHub repository AmreetKumarkhuntia/mcp-da-vinci (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,349 tokens to every session, about $0.0067 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens