FRENES

Image, video and audio · MCP server

MCP video: MCP server, setup and security

MCP video is an open-source MCP server published on GitHub that lets an AI agent edit videos locally with captions, effects and workflow quality checks. Its repository has 220 stars and its last commit is from October 24, 2026 and it is licensed under Apache-2.0.

Actively maintained

What MCP video does

According to its repository: “Local, guardrailed video editing: FFmpeg edits, captions, audio, effects, Hyperframes, repurposing, resumable workflows, quality gates and provenance receipts.”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. MCP video is listed under Image, video and audio, a category of 67 servers in the directory, where it ranks #19 by stars.

Topics declared by the repository: ai-agents, claude, claude-code, cursor, ffmpeg, python.

Installing and connecting MCP video

Distribution modes declared in the official MCP registry:

  • PyPI package (Python, started with uvx or pip)

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: Python. Listed systems: macOS, Windows, Linux.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to MCP video. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on March 21, 2026, the KyaniteLabs/kinocut repository has 220 stars and 47 forks, with 8 open issues. It has more stars than 79% of the servers in the directory. It received changes this month. Version published in the registry: 1.6.19 (October 24, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

ScreenpipeScreenpipe : 22.1K22.1KFunASRFunASR : 20.8K20.8KRemove AI WatermarksRemove AI Watermarks : 6.1K6.1KOpenScreenOpenScreen : 4.9K4.9KOpenPostOpenPost : 755755FableCutFableCut : 746746Anki MCP ServerAnki MCP Server : 531531MCP youtube transcriptMCP youtube transcript : 492492MCP videoMCP video : 220220
GitHub stars of the most followed servers in the category (log scale); MCP video in orange. Checked October 25, 2026.

Verdict

MCP video is one of the most solid servers in its category: followed, maintained and well framed.

Strengths

  • Active project: recent commit
  • Widely followed: 220 stars
  • Listed in the official MCP registry
  • Permissive licence (Apache-2.0)

Frequently asked questions

How do I install MCP video?

MCP video is distributed as PyPI package (Python, started with uvx or pip). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of KyaniteLabs/kinocut.

Is MCP video free?

The code is published under the Apache-2.0 licence and can be used free of charge.

Is MCP video safe?

No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.

Is it an official server?

It is published in the MCP registry under the verified namespace tech.kyanitelabs, which shows the publisher controls that domain.

What are the alternatives to MCP video?

In the same category: OpenScreen, Remove AI Watermarks, FunASR, and Oh My Cassette. OpenScreen scores higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score