Let your AI assistant read, build and edit CapCut desktop projects.
About
mcp-capcut is an MCP server for CapCut desktop on Windows and macOS. It lets AI assistants such as Claude Code read, create and edit CapCut projects. The assistant can add video, audio, images, text, subtitles, stickers, effects and keyframes. You then open the result in CapCut to review and export it. It is one native binary with FFmpeg bundled, so there is no Python, Node runtime or background service to install. Install it with `npm install -g mcp-capcut` or run it with `uvx mcp-capcut`. Your projects and media stay on your computer. It is for creators who edit in CapCut and want an assistant to do the repetitive work: rough cuts, captions, title cards and batch changes across a timeline. Linux is not supported, because CapCut desktop runs only on Windows and macOS.
Security Report
The launcher code is clean and small: it spawns a platform binary with fixed paths, passes MCP through the official SDK, and has one pinned dependency. The main concern is that the tools and licence check live in prebuilt native binaries and FFmpeg executables that were not provided for review and have no integrity verification, so their behaviour cannot be audited from this source. The binaries also receive the full process environment, including MCP_LICENSE_KEY. Package verification found 2 issues.
3 files analyzed · 8 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
What You'll Need
Set these up before or after installing:
Environment variable: MCP_LICENSE_KEY
Purchase above for keyHow to Install
Install instructions and configuration are available after purchase.
Getting Started
Once installed, try these example prompts and explore these capabilities:
- 1"List my CapCut projects and describe the most recent one."
- 2"Make a new CapCut project called Trip Recap from the clips in ~/Videos/trip, 3 seconds each, with a title card at the start."
- 3"Transcribe interview.mp4 and add the captions to a new project called Interview."
- 4"Add a zoom-in keyframe to the first clip of Trip Recap."
- 5Tool: capcut_status: shows the licence state and whether CapCut, FFmpeg and transcription are ready
- 6Tool: capcut_list_projects: lists the CapCut projects on this computer
- 7Tool: capcut_describe_project: summarises a project's timeline in plain language
- 8Tool: capcut_create_draft / capcut_add_video / capcut_add_text / capcut_save_draft: build a new project step by step and save it to CapCut
- 9Tool: capcut_edit_project: change, move or remove items in an existing project
- 10Tool: capcut_transcribe: turns speech in a media file into captions (needs whisper.cpp)
Reviews
No reviews yet
Be the first to review this server!
More Content & Media MCP Servers
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
MCP Marketplace
Freeby mcp-marketplace · Developer Tools
Search and install MCP servers from inside your AI client.
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
by Lharries · Communication
Read, search, and send WhatsApp messages through your AI assistant
FinAgent
Freeby mcp-marketplace · Finance
Free stock data and market news for any MCP-compatible AI assistant.
Memory
Freeby Modelcontextprotocol · Productivity
Knowledge graph-based persistent memory across sessions