cursorrules

Operating rules for the DaVinci Resolve MCP server, an add-on that lets an AI assistant work with the video-editing program. They route different jobs to the appropriate workflow and set safety rules for original media.

In plain words
What is it for?
Guiding AI work on editing, color correction, media, Fusion, delivery, and other Resolve tasks while keeping project and source-media handling consistent.
Why use it?
They reduce mistakes caused by using the wrong workflow or relying on outdated reference details. They also prevent source footage from being modified or replaced unless the user explicitly requests it.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/mrsuber/davinci-resolve-mcp/cursorrules
Clone the repo
git clone --depth 1 https://github.com/mrsuber/davinci-resolve-mcp

Made for: Cursor.

Per session 715 This file is loaded in full into every session.
When invoked 715 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 91% copy Near-identical to another mod 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 $0.00715 $0.00715
Opus 5 $0.00358 $0.00358
Sonnet 5 $0.00143 $0.00143
Haiku 4.5 $0.00072 $0.00072

Measured yesterday against content hash 35397528b37d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

Origin

This is a copy

91% identical to cursorrules — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursorrules · 21 lines

How it starts

The opening of the file, as written. The whole thing — 21 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DaVinci Resolve MCP — agent rules

This is the DaVinci Resolve MCP server: a Python MCP server (34 compound tools, 341 granular in --full mode) driving Resolve via its scripting API, plus an offline Node "advanced" server (18 tools) that authors .drp/.drt/.drx files and patches the project DB with no Resolve running. Kernel coverage: 136 guarded workflow actions.

  • Canonical agent brief: AGENTS.md. Operating reference: docs/SKILL.md. Per-action depth: docs/kernels/*. Advanced (offline) catalog: resolve-advanced/README.md.
  • Never modify, transcode, convert, proxy, relink, or create derivatives of source media unless explicitly asked. Analysis output goes to sidecars/scratch/the analysis project root.
  • Do not duplicate version numbers, tool counts, or kernel-action counts into prose — they drift. Reference the docs above.

Domain routing

On demand in any MCP client via slash prompts; full depth in docs/kernels/*:

  • Color / Grade (/color_grade_workflow) — grading, correcting, shot matching, developing looks, or applying/modifying LUTs, CDLs, DRX grades, or copied grades. Depth: docs/kernels/color-grade-kernel.md + docs/guides/color-decision-guide.md.
  • Timeline Edit (/timeline_edit_workflow) — cutting, trimming, pacing, duplicating/moving clips, copying ranges, building variants, tightening a cut, or generating an editorial changelist. Depth: docs/kernels/timeline-edit-kernel.md + docs/guides/editorial-decision-guide.md.
  • Conform / Interchange (/conform_workflow) — importing/relinking editorial, checking a conform against a reference, repairing reversed/retimed subclips, tracing grades across a re-conform, or QCing a conformed timeline. Depth: docs/kernels/timeline-conform-interchange-kernel.md.
  • Delivery / Deliverable QC (/delivery_workflow) — preparing render jobs, validating render settings, QCing a finished render vs spec, building render manifests, expanding texted/textless/stems deliverables, verifying media ingest, or producing a provenance/episode report. Depth: docs/kernels/render-deliver-kernel.md.
  • Fusion Composition (/fusion_workflow) — building or editing Fusion comps — titles, motion graphics, VFX, merges, masks, trackers. Depth: docs/kernels/fusion-composition-kernel.md.
  • Audio / Fairlight (/audio_workflow) — setting audio properties, syncing audio, isolating voice, generating subtitles, planning Fairlight tracks/buses, checking loudness, routing buses, or splitting/trimming/converting audio. Depth: docs/kernels/audio-fairlight-kernel.md.
  • Media Pool / Ingest (/media_pool_workflow) — importing media, building multicam timelines, organizing/relinking clips, normalizing metadata, or verifying/inventorying a card before ingest. Depth: docs/kernels/media-pool-ingest-kernel.md + docs/guides/multicam-setup-guide.md.
  • Media Analysis (/analyze_media) — reading or analyzing source media (technical, visual, or transcription) to inform Resolve actions. Depth: docs/kernels/README.md + docs/guides/media-analysis-guide.md.

Read the full file on GitHub · 21 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. yesterday First seen · 21 lines · 715 tokens per session scan A 35397528b37d

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository mrsuber/davinci-resolve-mcp (0 stars, last pushed 26d ago), licensed MIT. It adds 715 tokens to every session, about $0.0036 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to cursorrules, differing in 2 lines, and is treated as a copy.