yt-mem-ai MCP Server

by dasein108 Your server? Claim it

local only

yt-mem-ai runs on your own machine — the client starts it, so there is no endpoint to ping. 84 installs a week from pypi. Last commit 23 Aug 2026.

Local YouTube memory: transcribe, embed and search videos, with summaries and highlights.

Installs per day peak 87 · avg 20 · -65% w/w

a month agotoday

Installs / week

pypi · yt-mem-ai

Stars

0 open issues

23 Aug 2026

Last commit

from GitHub

MIT

License

Typst

What the code does

We read the source, 5 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command yt_mem_ai/frame.py:63, [пакет] yt_mem_ai/frame.py:63

    subprocess.run(argv, check=True)

Builds a file path from a variable yt_mem_ai/supercut.py:155, [пакет] yt_mem_ai/supercut.py:155

        raw = os.path.join(workdir, f"{i:03d}_raw.mp4")

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add yt-mem-ai -- uvx yt-mem-ai

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "yt-mem-ai": {
      "command": "uvx",
      "args": [
        "yt-mem-ai"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.yt-mem-ai]
command = "uvx"
args = ["yt-mem-ai"]

.cursor/mcp.json

{
  "mcpServers": {
    "yt-mem-ai": {
      "command": "uvx",
      "args": [
        "yt-mem-ai"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "yt-mem-ai": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "yt-mem-ai"
      ]
    }
  }
}

Alternatives to yt-mem-ai

same job, measured the same way

BibiGPT

by jimmylv

Summarize, transcribe and search YouTube, Bilibili, TikTok, podcasts and other videos with AI.

answering

YouTube Translate

by brianshin22

Transcripts, translations, summaries, subtitles, and search for public YouTube videos.

answering

Wisprs

by wisprs

Transcribe audio, video and YouTube links, then search, summarize and export your transcripts.

answering

YouTube Transcripts, Search & Summaries

by gunnargray-dev

YouTube transcripts, video search, chapters and extractive summaries. No YouTube API key, no LLM.

answering

youtube-media

by nexlab

Search YouTube, read video metadata, and fetch transcripts with language preferences

answering

BibiGPT YouTube Video Summarizer

by bibigpt

AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.

answering

Scribefy

by mkirovbg

Search YouTube, get video metadata, and extract timestamped transcripts for AI workflows.

53 installs/wk local only

YouTube Search Transcripts

by fernandoguiraud16-coder

Transcripts of the top YouTube videos for a keyword, with date, length and sort filters.

answering

yt-mem-ai — questions

Answers built from our own checks of this server.

Why is there no uptime for yt-mem-ai?

yt-mem-ai runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package yt-mem-ai was installed 84 times last week.

How do I connect yt-mem-ai?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls yt-mem-ai straight from pypi; nothing to host, nothing to sign up for.

How many people use yt-mem-ai?

The pypi package yt-mem-ai was installed 84 times in the last week. Week over week that is -65%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is yt-mem-ai open source?

Yes — it is published under the MIT licence, written in Typst and 7 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.