Enterprise DNA Enterprise DNA
M MCP Servers Developer low

tydude001/proofcut

by Various

An AI video editor that proves its cuts. Your recordings to a finished, mastered film, cut by transcript, on your own machine, by you or an agent. Every render is checked against t

MCP

tydude001/proofcut

Added 21 Sept 2026

#claude-code #ffmpeg #local-first #mcp #mcp-server #opentimelineio #video-editing #whisper

Overview

An AI video editor that cuts recordings by transcript and verifies every render against the edit. Runs locally on your own machine, usable by a human or an agent. Produces a finished, mastered film from raw recordings.

Best for

Best for
Developers and agents who want local, transcript-based video editing with built-in render verification.

Use cases

  • Cut interview recordings by searching the transcript
  • Automate video editing with an agent on a local machine
  • Verify that exported renders match the intended edit

How to use

Install

uvx proofcut doctor

Tools exposed

  • auto-editor

Tested with

Claude Code, ChatGPT

Notes

An AI video editor that cuts recordings by transcript and verifies every render against the edit. Runs locally on your own machine, usable by a human or an agent. Produces a finished, mastered film from raw recordings.

3 stars on GitHub. Last updated 2026-09-21.

Use cases

  • Cut interview recordings by searching the transcript
  • Automate video editing with an agent on a local machine
  • Verify that exported renders match the intended edit

Pros

  • Runs locally, so footage stays on your machine
  • Every render is checked against the edit, reducing silent errors
  • Transcript-based cutting makes editing searchable and precise

Cons

  • Only 3 GitHub stars, so it is early-stage and likely rough
  • Python-only, which may require setup and technical skill
  • No documented support for formats or platforms, so compatibility is unclear

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Runs locally, so footage stays on your machine
  • Every render is checked against the edit, reducing silent errors
  • Transcript-based cutting makes editing searchable and precise

Cons

  • Only 3 GitHub stars, so it is early-stage and likely rough
  • Python-only, which may require setup and technical skill
  • No documented support for formats or platforms, so compatibility is unclear

Pairs with

Other entries in the index that connect to this one. Click through to see the chain.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks