What is mcp-video-editing-assistant CLAUDE.md?

A set of instructions for Claude Code in a video-editing assistant project. It describes the project structure, its Model Context Protocol servers, and its DaVinci Resolve integration.

Use it when changing or reviewing the assistant's servers, editing-behaviour tracking, persistent JSON data, or DaVinci Resolve integration.

It gives the coding agent project-specific context about how the assistant tracks editing work and connects to DaVinci Resolve.

How JossBen/mcp-video-editing-assistant configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to JossBen/mcp-video-editing-assistant. 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/JossBen/mcp-video-editing-assistant/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/JossBen/mcp-video-editing-assistant

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jossben/mcp-video-editing-assistant/claude-md/github.svg)](https://agentmods.dev/instructions/jossben/mcp-video-editing-assistant/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jossben/mcp-video-editing-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/jossben/mcp-video-editing-assistant/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jossben/mcp-video-editing-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/jossben/mcp-video-editing-assistant/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 757 This file is loaded in full into every session.

When invoked 757 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.

Model	Per session	Once invoked
Fable 5.1	$0.00757	$0.00757
Opus 5	$0.00378	$0.00378
Sonnet 5	$0.00151	$0.00151
Haiku 4.5	$0.00076	$0.00076

Measured 9d ago against content hash b170970a0d2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-video-editing-assistant 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 9d 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is an MCP (Model Context Protocol) Video Editing Assistant that integrates with DaVinci Resolve to learn from editing behavior and provide intelligent assistance for film/TV post-production workflows.

Architecture

The project consists of three main MCP servers:

server.py: Basic MCP server template with echo functionality
davinci_resolve_mcp.py: DaVinci Resolve integration server with real-time timeline analysis, workflow learning, and AI-powered insights
editing_watcher.py: General editing behavior tracker using file system monitoring
enhanced_server.py: Enhanced file operations server

The architecture follows MCP patterns with async handlers for tools and resources. Each server tracks different aspects of editing workflows and maintains persistent data in JSON files.

Key Components

DaVinci Resolve Integration

Uses DaVinci Resolve Python API (fusionscript)
Tracks timeline changes, cut patterns, tool usage across Edit/Color/Fairlight/Deliver pages
Platform-specific API paths: macOS (/Applications/DaVinci Resolve/), Windows (C:\Program Files\Blackmagic Design\DaVinci Resolve\), Linux (/opt/resolve/libs/Fusion/)

Behavior Tracking

ResolveEditingTracker class for DaVinci-specific tracking
EditingBehaviorTracker class for general editing patterns
File system monitoring with watchdog for project changes
JSON persistence for learned patterns and insights

Development Commands

Environment Setup

# Create and activate virtual environment
python3 -m venv venv
source venv/bin/activate  # macOS/Linux
# or
venv\Scripts\activate     # Windows

# Install dependencies
pip install -r requirements_editing.txt  # Full editing features
# or
pip install -r requirements.txt          # Basic MCP only

DaVinci Resolve Setup

# Configure Resolve API integration
python setup_resolve_integration.py

Read the full file on GitHub · 91 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.

9d ago First seen · 91 lines · 757 tokens per session scan A b170970a0d2b

Subscribe to this mod's changes

mcp-video-editing-assistant CLAUDE.md is an instructions file published in the GitHub repository JossBen/mcp-video-editing-assistant (1 stars, last pushed 1y ago), licensed MIT. It adds 757 tokens to every session, about $0.0038 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.

Creative and media

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

mcp-video-editing-assistant: Instructions file for Claude Code