MCP.Market

yt-mem-ai MCP server

by dasein108·io.github.dasein108/yt-mem-ai·v0.6.3·7 stars
No reviews yet

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

A88/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
Growing

7 stars71 downloads/wk

Reviews

Write one

Nobody has reviewed yt-mem-ai yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

yt-mem-ai tools (21, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • analyze_video

    Ingest a YouTube video and return its transcript so you can summarize, highlight, answer questions about, or make a presentation from it.

  • channel_list

    Enumerate a channel's recent uploads (does NOT ingest them).

  • compile

    Compile deep-linked highlights from summarized videos (fast, no download).

  • config_get

    Get one setting's effective value and where it comes from (env/project/global/default).

  • config_list

    List every yt-mem-ai setting with its effective value, source, and description.

  • config_set

    Set a yt-mem-ai setting (e.g. WEBSHARE_PROXY_USERNAME, YT_EMBEDDING_MODEL).

  • config_unsetwrite action

    Remove a setting from the global (or scope="project") config file.

  • discover

    Discover new subscription uploads and store them as 'discovered'.

  • dislike

    Mark a video as disliked (feeds taste-based recommendations).

  • fetch

    Download + transcribe + embed + store a single video (idempotent).

  • fetch_pending

    Batch download + transcribe + embed all pending 'discovered' videos.

  • frame

    Grab a still frame from an ingested video at a timestamp (needs yt-dlp + ffmpeg).

  • like

    Mark a video as liked (feeds taste-based recommendations).

  • list_videos

    List stored videos, optionally filtered by status/date/channel and capped.

  • recommend

    Rank unrated fetched videos by learned taste (like − dislike centroid).

  • reembed

    Rebuild all chunk embeddings with the current YT_EMBEDDING_* config.

  • save_summary

    Persist a model-generated summary for a video (marks it 'summarized').

  • search

    Search transcript chunks. mode = hybrid | vector | fts.

  • show

    Return stored metadata + full transcript for a video (or {error: ...}).

  • status

    Return video counts grouped by lifecycle status.

  • supercut

    Render an actual video supercut of highlights (SLOW: re-downloads clips + ffmpeg).

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan23 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 32 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How yt-mem-ai compares

Against every graded Web search MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 80% of 3,470 Web search servers
Tools
21
the typical Web search server has 5
Tools that change things
5%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
7
more than 83% of 1,786 Web search servers
Downloads a week
71
more than 49% of 827 Web search servers with a package

What its tools let an agent do: 19 read · 1 create · 1 change

Install yt-mem-ai in Claude Code, Cursor or VS Code

claude mcp add yt-mem-ai -- uvx yt-mem-ai
Add to Cursor

What the publisher says

From the yt-mem-ai repository's README, as published. We do not edit it. Read it on GitHub

yt-mem-ai — a local YouTube memory for your AI assistant

<!-- mcp-name: io.github.dasein108/yt-mem-ai -->

Give Claude, Codex, Cursor, or any MCP host the ability to watch YouTube for you: transcribe videos, remember them, follow your subscriptions, and turn all of it into summaries, timestamped highlights, Q&A, digests, and video reels. Everything runs on your machine — no cloud service, no API key.

One command, two questions — here it's wiring the skills into Codex.

Example — "make a presentation from this video" (Andrej Karpathy: From Vibe Coding to Agentic Engineering, Sequoia, 30 min) → 13 slides, PDF, every quote timestamped from the transcript. Ingest to deck in one request.

Table of Contents

  • Features
  • How to install
  • Getting Started
  • Usage
  • Examples
  • Configuration
  • Under the hood

Features

language), offline Whisper when they don't.

  • 🎧 Transcribes any video — YouTube captions when they exist (fast, any

locally, so your library stays searchable forever. Nothing leaves your machine.

  • 🧠 Remembers what you watched — every transcript is stored and indexed

answer with a timestamp you can jump to.

  • 🔎 Finds the moment — ask "what did that video say about X" and get the

one digest.

  • 📡 Follows your subscriptions — picks up new uploads and turns the day into

decks, all in the video's own language, using the model you already pay for.

  • ✍️ Your assistant does the writing — summaries, highlights, Q&A, slide

your own library.

  • ❤️ Learns your taste — like or dislike videos and get recommendations from

supercut reels.

  • 🎬 Makes media too — clickable highlight docs, still frames, and rendered

Antigravity, OpenClaw, Hermes: skills or MCP, your pick.

  • 🔌 Works with your tools — Claude Code, Claude Desktop, Codex, Cursor,

How to install

1. Connect your assistant ⭐

curl -LsSf https://raw.githubusercontent.com/dasein108/yt-mem-ai/main/install.sh | sh

An interactive wizard opens. Pick what you want, tick your apps, press enter:

step 1/2 — what (pick one)     step 2/2 — where (tick any)
> Plugin  skills + CLI         [x] Claude Code    [ ] Claude Desktop
  MCP     typed tools          [x] Codex          [ ] Cursor
                               [ ] Antigravity    [ ] OpenClaw   [ ] Hermes

Plugin teaches your assistant to act on plain requests — "summarize this video". MCP gives it a set of tools instead. Not sure? Start with Plugin; you can run the wizard again for the other.

It installs everything it needs, ticks what you already have, and removes anything you untick (it shows a plan and asks first). Then restart the app and try: summarize 'https://youtu.be/…'.

Already know what you want? Skip the questions:

curl -LsSf https://raw.githubusercontent.com/dasein108/yt-mem-ai/main/install.sh \
  | sh -s -- --plugin --claude-code --codex
curl -LsSf https://raw.githubusercontent.com/dasein108/yt-mem-ai/main/install.sh \
  | sh -s -- --mcp --claude-desktop --cursor

Hosts: --claude-code --claude-desktop --codex --cursor --antigravity --openclaw --hermes, or --all. Full flag list and uninstall notes: integrations/README.md. Rather have an agent do it? Paste integrations/PROMPT.md into any assistant.

2. MCP by hand — one config entry, self-installing

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

yt-mem-ai: common questions

Is yt-mem-ai MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the yt-mem-ai safety report
How do I install yt-mem-ai?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does yt-mem-ai need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is yt-mem-ai maintained?
The last commit was 73 days ago (2026-08-23). The latest release is v0.6.3.
What can I use instead of yt-mem-ai?
Servers from other publishers that do the same job: Brave Search MCP server, Minutes MCP server and Misakanet MCP server.
How does yt-mem-ai compare with other Web search MCP servers?
safety score 88/100 (higher than 80% of 3,470 Web search servers); tools 21 (the typical Web search server has 5); tools that change things 5% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to yt-mem-ai

Same job from other publishers: the closest match first, then the best rated.

  • Brave Search
    Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more.
    A
  • Minutes
    The private, owned conversation-memory layer for AI. Record, transcribe, and search every meeting.
    A
  • Misakanet
    Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.
    A
  • Marm
    Universal MCP Server with advanced AI memory capabilities and semantic search.
    A
  • Link
    Local personal memory for agents as MCP tools — remember, recall, search, context, graph traversal.
    A