BrainTube

io.github.lildaddyoPublished by GitHub account lildaddyov3.15.6Updated Oct 30, 2026

Persistent AI memory over your saved YouTube videos, podcasts, articles and PDFs for any MCP client.

The publisher's own server: BrainDog

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

BrainTube gives an assistant persistent, searchable memory over your saved YouTube videos, podcasts, articles and PDFs, with citations back to sources.

What you can do
  • Search your saved corpus with semantic and keyword search, with citations to the source items
  • Save new items from the assistant, add notes and apply tags in the same session
  • Traverse a knowledge graph and related items across your saved material
  • Read session context such as expertise profile, recent activity and resurfacing suggestions
  • Discover and run additional read-only tools on demand through the find-tools and run-tool helpers
When to use it
Useful when you want an assistant to draw on your own library of videos, podcasts, articles and PDFs instead of starting each conversation cold, and when you want it to save findings back into that library.
Requirements
A remote Streamable HTTP endpoint; no local install. A BrainTube account, plus either OAuth 2.0 sign-in (authorization code with PKCE) or a BrainTube API key sent in the X-BrainTube-Token header. Network access to the endpoint.
Before you install
The API key in the X-BrainTube-Token header is a secret; prefer OAuth where the client supports it. The assistant can write to your library by saving items, adding notes and tagging, so review changes. Your saved content and queries are sent to BrainTube's servers.

Installation

In SourceWeft

  1. Open BrainTube in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.lildaddyo%2Fbraintube-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "braintube": {
      "type": "http",
      "url": "https://mcp.brain-tube.com/mcp"
    }
  }
}

README

BrainTube MCP Server

Save once. Query anywhere. BrainTube compiles what you watch, read and listen to — YouTube videos, podcasts, articles, PDFs — into a persistent, searchable knowledge base, and this MCP server lets your AI search it and save to it over one endpoint.

What it does

Your AI can search and cite your own corpus instead of starting every conversation cold:

  • Semantic + keyword search over everything you've saved, with citations back to the source
  • Save from your AI — your AI can save what it finds into BrainTube, add notes and tag items in the same session
  • Knowledge graph & related-item traversal across your corpus
  • Session context — expertise profile, recent activity, and resurfacing tools
  • Per-user isolation — JWT-scoped access; you only ever see your own corpus

Quickstart

  1. Create an account at brain-tube.com and get an API key (or use OAuth from a compatible client).
  2. Add the server to your MCP client:
json
{  "mcpServers": {    "braintube": {      "type": "http",      "url": "https://mcp.brain-tube.com/mcp",      "headers": { "X-BrainTube-Token": "bt_..." }    }  }}

Tested with Claude and ChatGPT; any client that speaks MCP streamable HTTP uses the same endpoint. In clients with OAuth support, just add the endpoint URL and sign in when prompted.

Claude Code — one command:

bash
claude mcp add --transport http --scope user braintube https://mcp.brain-tube.com/mcp   --header "X-BrainTube-Token: bt_..."

Claude.ai — Customize → Connectors → + Add → Add custom connector, paste the endpoint, sign in. No API key needed.

ChatGPT — Settings → Plugins → Add → Add custom MCP server. Paste https://mcp.brain-tube.com/mcp, choose OAuth, tick the risk box, Create, then Connect and sign in to BrainTube. No API key needed. ChatGPT uses the search and fetch tools and cites each answer back to your saved item.

Tool profiles — by default a session gets 12 tools: the everyday search, read and save tools, plus braintube_find_tools and braintube_run_tool, which reach the other read-only tools on demand. To register every tool directly, add ?tools=full to the endpoint (https://mcp.brain-tube.com/mcp?tools=full) or send the header X-BrainTube-Tools: full.

Step-by-step setup for each client, plus how BrainTube compares with other MCP memory servers: How to give Claude long-term memory with MCP.

Links

Source: README.md at commit af132a9

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

4
  1. v3.15.6LatestOct 30, 2026
  2. v3.14.12Oct 19, 2026
  3. v3.14.10Oct 18, 2026
  4. v3.12.3Sep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.

Other Brain integrations

BrainDog

dog.brainOfficial publisher

BrainDog is a hosted record of projects, decisions and money that connected AI agents read before starting work and write their results into.

Streamable HTTPWeb executableAuth
FinanceCredential requiredNov 5, 2026

Codebase Brain

Published by GitHub account Nomannazir

Indexes a local or public git codebase so an assistant can search it, trace git history, check change impact and find stale docs, all with path:line citations.

STDIODesktop only
Developer ToolsNot validated yetNov 7, 2026

Personal Brain

Published by GitHub account zhang-liz

Gives an AI assistant memory of your professional network, stored as a graph in FalkorDB, so it can look up contacts, find people by topic, and save who you…

STDIODesktop only
Databases3 toolsNov 6, 2026

Second Brain

Published by GitHub account ara-5

Shared Graph-RAG memory for AI agents: markdown vault, wikilink recall, tasks, messaging.

STDIODesktop only
AI & ML12 toolsNov 7, 2026

Make0 Brain

Published by GitHub account make0-official

A local, offline memory server that lets Claude Code, Cursor, Codex and other MCP agents share one versioned store of durable facts.

STDIODesktop only
Developer ToolsNot validated yetNov 7, 2026