capcut-mcp-server-extended: Instructions file for Claude Code

CLAUDE.md

capcut-mcp-server-extended CLAUDE.md is an instructions file for Claude Code from MigueDuque/capcut-mcp-server-extended. It costs 4,456 tokens per session, scanned A, original, MIT.

A video-editing server that lets an AI assistant control CapCut Pro through a backend service, including workflows for vertical short videos.

In plain words
What is it for?
Use it to automate short-form video production, combine editing steps into tool calls, and build or run the TypeScript server.
Why use it?
It reduces manual editing steps for tasks such as subtitles, animated text, talking-head videos, and reusable editing presets.

Instructions file for Claude Code

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

This is MigueDuque/capcut-mcp-server-extended's own configuration. It tells Claude Code how to work on capcut-mcp-server-extended 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 capcut-mcp-server-extended configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MigueDuque/capcut-mcp-server-extended. 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/MigueDuque/capcut-mcp-server-extended/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MigueDuque/capcut-mcp-server-extended

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 capcut-mcp-server-extended CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/migueduque/capcut-mcp-server-extended/claude-md.svg)](https://agentmods.dev/instructions/migueduque/capcut-mcp-server-extended/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/migueduque/capcut-mcp-server-extended/claude-md"><img src="https://agentmods.dev/badge/instructions/migueduque/capcut-mcp-server-extended/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,456 This file is loaded in full into every session.
When invoked 4,456 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 $0.04456 $0.04456
Opus 5 $0.02228 $0.02228
Sonnet 5 $0.00891 $0.00891
Haiku 4.5 $0.00446 $0.00446

Measured 8d ago against content hash 5bb9ca82ad62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

capcut-mcp-server-extended 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 8d 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 · 396 lines

How it starts

The opening of the file, as written. The whole thing — 396 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

capcut-mcp-server-extended is a Model Context Protocol (MCP) server that bridges AI assistants (Claude, etc.) with CapCut Pro video editing via a VectCutAPI backend. It is a fork of atx-guy/capcut-mcp-server extended toward a professional video automation tool, with a focus on talking head / reels content: vertical 1080×1920 videos, auto-subtitles, animated text, and composable presets that collapse multi-step workflows into a single tool call.

The end goal is to let an AI assistant produce a fully-edited short video by issuing a handful of MCP tool calls — no manual CapCut interaction required.


Commands

# Build (compile TypeScript → dist/, make dist/index.js executable)
npm run build

# Development (watch mode, recompiles on change)
npm run dev

# Run the compiled server
npm start

No test scripts are configured. The server starts and communicates over stdio (default) or HTTP. Always run npm run build after every code change and confirm zero errors before committing.


Architecture

Transport modes (set via TRANSPORT env var):

  • stdio (default) — for Claude Desktop / local MCP clients
  • http — listens on PORT (default 3000)

Key env vars: CAPCUT_API_URL (default http://localhost:9001), PORT, TRANSPORT

VectCutAPI backend: runs at http://localhost:9001. Useful endpoints:

  • GET /get_font_types — returns the full list of supported font names
  • POST /create_draft, /add_video, /add_text, /add_keyframe, /save_draft, etc.

Data flow

MCP Client
  → src/tools/index.ts          (tool registration + Zod validation)
  → src/tools/presets.ts        (high-level composite tools — Phase 3+)
  → src/services/api-client.ts  (axios singleton, 60 s timeout)
  → VectCutAPI backend          (http://localhost:9001)

Source layout

File / Dir Role
src/index.ts Entry point; stdio/HTTP transport setup — do not modify
src/tools/index.ts All 13 MCP tool definitions; formatResponse / handleError helpers
src/tools/presets.ts High-level composite tools (Phase 3+)
src/schemas/index.ts Zod schemas for every base tool input
src/services/api-client.ts Singleton apiClient; maps tool calls → POST endpoints — do not modify
src/types.ts TypeScript interfaces (DraftConfig, VideoTrack, ResponseFormat, …)
src/constants.ts API_BASE_URL, defaults, supported formats, effects, transitions
src/presets/typography.ts [Phase 1 ✅] Three named text styles; font = Poppins_Bold
src/presets/animations.ts [Phase 2 ✅] Keyframe animation sequences (popInUpper)
src/utils/validators.ts [Phase 5] Path validation, Windows↔Unix helpers
utils_py/transcribe_audio.py Whisper word-level transcription; outputs JSON word list
utils_py/inspect_draft.py Reads draft_content.json; extracts audio path, duration, fps
utils_py/validate_project.py Checks that all media files referenced in a draft exist

Read the full file on GitHub · 396 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. 8d ago First seen · 396 lines · 4,456 tokens per session scan A 5bb9ca82ad62

Subscribe to this mod's changes

capcut-mcp-server-extended CLAUDE.md is an instructions file published in the GitHub repository MigueDuque/capcut-mcp-server-extended (5 stars, last pushed 5mo ago), licensed MIT. It adds 4,456 tokens to every session, about $0.0223 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

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

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

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

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 · 7,104 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