SmartCut MCP (CapCut talking-head)
Reads CapCut's auto-captions to remove silences and duplicate takes directly in a CapCut project, ideal for talking-head videos.
How to set it up
- Generate subtitles in CapCut (Text > Auto Captions), then close CapCut.
- Set up the Python venv and add the server to Claude.
- Ask: 'Smart cut my <project name>'.
This is a plain-English summary of the project's own instructions. Commands and versions change, so always follow the current README at the source link.
Safety notes
- Modifies the project in place with no backup. Duplicate it in CapCut first.
- Optional OpenAI API key for better duplicate detection.
General rule: open a duplicate of your project before letting any agent make changes, and read what a script does before approving it.
Alternatives and related tools
VectCutAPI (CapCut/Jianying API)
Editing API and skills that add subtitles, images, picture-in-picture, AI voiceover and filters to CapCut/Jianying drafts; backend for several CapCut MCP servers.
cutcli cookbook
Cookbook, JSON templates and prompts for cutcli, a CapCut/Jianying draft CLI, to generate editable drafts from code or an MCP agent.
CapCut MCP Server — Extended
Fork of atx-guy/capcut-mcp-server adding parametrized typography, animation presets and full talking-head production workflows for Claude Code.
capcut-mcp (JmsLdrn)
Reads and edits CapCut desktop drafts: add/move/trim/split clips, text, audio and images, set transforms, validate and save, by cloning real templates from an existing draft.
The AgentCut weekly
New AI connectors for After Effects, Premiere, Resolve and CapCut, tested setup notes, and what broke after app updates. One email a week.