ravishu5 GitHub avatar

second-brain-mcp

ravishu5

Second Brain MCP is an MCP server that ingests YouTube videos and podcasts into a local SQLite database, enabling an AI assistant to answer questions about their content with timestamped deep links.

Stars

5

7-day growth

No data

Forks

0

Open issues

0

License

MIT

Last updated

2026-07-29

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It showcases the new stateless MCP spec (2026-07-28) with multi-round-trip approval for deletion, requires no API keys or cloud accounts, and provides private, full-text search across watch history with exact timestamp references.

Who it is for

  • Knowledge workers who watch many tutorials and talks
  • Podcast listeners who want to search spoken content
  • Developers building MCP-based tools or exploring the new stateless spec
  • Researchers needing to reference video content quickly

Use cases

  • Ask your AI assistant 'What did that video say about salary negotiation?' and get an answer with a timestamp
  • Search across your entire YouTube watch history for specific topics
  • Get a weekly digest of everything you recently watched or listened to
  • Delete a video from your memory with explicit user approval using MRTR

Strengths

  • Privacy-first: all data stored locally in SQLite, no cloud or API keys needed
  • Zero-config for YouTube: fetches captions directly without keys
  • Full-text BM25 search with timestamped chunks that link to exact moments
  • Demonstrates cutting-edge MCP features like statelessness and multi-round-trip approval

Considerations

  • Only supports YouTube and podcasts (via RSS + local Whisper); other sources not yet available
  • YouTube videos without captions cannot be indexed
  • Podcast ingestion requires installing an optional Whisper dependency and local processing

README quick start

🧠 Second Brain MCP

Remember everything you watch and listen to.

A Model Context Protocol server that turns YouTube videos and podcasts into a private, searchable memory — built on the brand-new stateless MCP spec (2026-07-28).

Paste a link once. Ask about it forever.

"What did that video I watched last month say about salary negotiation?"

🧠 → "At [12:43] in Never Split the Difference — Chris Voss, he says never to accept the first offer without anchoring high…" — with a deep link that jumps to the exact second.

Why

You watch hours of talks, tutorials, and podcasts — and a week later you can quote none of it. Browser history remembers that you watched something; nothing remembers what it said. Second Brain gives your AI assistant total recall over everything you've ever watched or listened to:

  • 🎯 Ask across your whole watch history — answers come back with timestamps and deep links to the exact moment.
  • 🔒 Private by design — one local SQLite file. No cloud, no accounts, no API keys. Podcast audio is transcribed locally.
  • Zero-key ingestion — YouTube captions are fetched directly; nothing to configure.
  • 🗑️ Nothing is deleted without you — destructive operations use the spec's new multi round-trip (MRTR) approval flow.

Quickstart

1. Install

Option A — as a tool, straight from GitHub (recommended):

uv tool install git+https://github.com/ravishu5/second-brain-mcp

This installs the second-brain command into ~/.local/bin. Find its absolute path — you'll need it below:

which second-brain     # e.g. /Users/you/.local/bin/second-brain

Option B — from a local clone (for hacking on it):

git clone https://github.com/ravishu5/second-brain-mcp
cd second-brain-mcp
python3 -m venv .venv && .venv/bin/pip install -e .

Your binary is then at /.venv/bin/second-brain.

2. Connect a client

Always use the absolute path to the binary. GUI apps (like Claude Desktop) don't inherit your shell's PATH, so a bare second-brain command often fails with "Failed to spawn process: No such file or directory".

Claude Code

claude mcp add second-brain -- /absolute/path/to/second-brain

Claude Desktop — Settings → Developer → Edit Config, then add:

{
  "mcpServers": {
    "second-brain":

Related repositories

Similar projects matched by category, topics, and programming language.

mereyabdenbekuly-ctrl
Featured
mereyabdenbekuly-ctrl GitHub avatar

clodex-ide

Clodex is an open-source, local-first agentic IDE that combines persistent AI tasks, code, terminal, browser, Git, models, memory, and governed execution in one Electron workspace, currently in technical preview.

AI & Machine LearningAI Agents
859
0xwilliamortiz
Featured
0xwilliamortiz GitHub avatar

openclaude-improved

OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.

AI & Machine LearningLarge Language Models
577
talivia-group
Featured
talivia-group GitHub avatar

talivia

Talivia is an open-source, self-hosted analytics platform that combines web analytics, session replay, and customer revenue tracking from multiple payment providers.

Web DevelopmentData & Databases
483