Deploy Concat: The Open-Source Local-First CapCut Alternative Scriptable via JSON-RPC & MCP
A viral local-first, open-source CapCut replacement with 11k+ GitHub stars! Concat eliminates subscription lock-in and cloud privacy risks. Native on Windows, macOS, and Linux, it features multi-track timeline editing, bezier keyframes, LUT grading, and built-in subtitle generation. Crucially, Concat exposes native JSON-RPC and MCP APIs, enabling AI coding agents (Claude Code, Cursor) to automate clip cutting, transitions, voice-track alignment, and batch exports via code or natural language.
Proprietary editors are subscription-locked, bloated, and walled off from AI agents. Concat provides a modern, fast, local-first GUI with native MCP and JSON-RPC APIs, empowering agents to perform deterministic, frame-accurate video editing locally.
Step-by-Step Action Checklist
0 / 4 CompletedI am integrating the open-source Concat editor with Claude Code / Cursor to build an automated video assembly pipeline. Please provide: 1) [Concat MCP Configuration]: Standard mcpServers JSON configuration plus a Python snippet demonstrating JSON-RPC socket connection to Concat; 2) [Silence Removal & Caption Timing Prompt]: Prompt directing the agent to parse Whisper timestamped transcript JSON, compute dead-air intervals >0.6s, and mark split keyframes; 3) [Multi-Track Assembly Script]: Python script using Concat MCP methods to position talking-head footage, B-roll overlays, animated text titles, and ducked background audio into an exported 1080x1920 reel.