MCP Setup

Connect your library to every AI you use

BrainTube runs a remote MCP server, so Claude, ChatGPT, Cursor and any Model Context Protocol client can read your knowledge base — and save what they find back into it. Works on the free plan.

Connect in one step Start free

What is MCP, in plain English?

MCP (Model Context Protocol) is an open standard — think of it as a USB-C port for AI assistants. Instead of every tool needing its own custom plugin for every chatbot, MCP gives them one shared plug. Connect BrainTube once, and any MCP-capable assistant can use it.

How it works

  1. You save videos to BrainTube; we transcribe, summarize and index them.
  2. You add our MCP server URL to Claude, Cursor, ChatGPT or another client, and sign in.
  3. When you ask a question, the assistant calls BrainTube for the relevant passages and answers using them.

Why people use it

  • No copy-pasting transcripts into a chat window.
  • Answers cite your own saved material, not the open web.
  • One library, reusable across every assistant you switch to.
  • You control access — revoke a client any time.

In short: MCP turns your BrainTube library into context your AI can read on demand, in the tool you already work in.

One integration, not twenty

BrainTube is AI-agnostic by design. It doesn't ship a connector per assistant — it speaks Model Context Protocol, the open standard clients are adopting. Any compliant client reads your library the day it ships MCP support. You're not waiting on our roadmap.

Any MCP client
Native Model Context Protocol. Same endpoint, same config. If your assistant speaks MCP, it works — no integration from us required.
Claude Desktop
Read summaries, search transcripts, and ask Claude to reason over your library.
Cursor
Pull engineering talks and tutorials into your coding workflow as live context.
ChatGPT
Connects in Developer mode, or via OpenAPI for custom GPTs. Both paths in testing.
Perplexity
Add BrainTube as a custom remote connector so answers can draw on your own saved material alongside the live web.
VS Code · GitHub Copilot
Native MCP support in Copilot agent mode — pull saved talks and docs in as context beside the codebase.
Gemini CLI
Add the endpoint to your settings.json and OAuth is discovered automatically. The Gemini chat app does not take custom connectors yet.
Codex CLI
Remote streamable-HTTP is supported — add the URL, then sign in with codex mcp login.

Setup in 60 seconds

BrainTube's MCP server is remote — there's nothing to install. Add the endpoint to your client and sign in when it asks. API keys are only for clients that can't sign in yet.

One step — sign in when your AI asks
OAuth

In Claude.ai, go to Settings → Connectors → Add custom connector. First type a name for it — BrainTube — then paste https://mcp.brain-tube.com/mcp in the URL field and sign in when prompted. No API key needed — Claude.ai connects via OAuth.

In ChatGPT, go to Settings → Connectors → Advanced, turn on Developer Mode, click Add connector and paste the same URL. Sign in when prompted.

Endpoint
streamable-http
https://mcp.brain-tube.com/mcp
Advanced — connect with an API key (Cursor · Claude Desktop · Gemini CLI · other clients)
JSON
{
  "mcpServers": {
    "braintube": {
      "type": "streamable-http",
      "url": "https://mcp.brain-tube.com/mcp",
      "headers": {
        "X-BrainTube-Token": "bt_your_key_here"
      }
    }
  }
}

Config file locations: Claude Desktop → ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows). Cursor → Settings → MCP → Add Server. Any client that speaks MCP streamable-http works with the same URL + X-BrainTube-Token header.

  1. 1Using Claude.ai or ChatGPT? Add the URL, sign in when prompted, and skip to step 4. For Cursor, Claude Desktop, CLI tools and any other client that can't sign in yet, create an API key at Settings → API Keys.
  2. 2Paste the config above into your MCP client's config (or add the URL + X-BrainTube-Token header through the client's UI).
  3. 3Replace bt_your_key_here with your real key and restart the client.
  4. 4Try: 'Summarize the last 5 videos I saved about pricing.'

Your library, every AI

One source of truth. Reachable from every assistant you talk to.

Get Started Free

Frequently asked

What is MCP and why does BrainTube use it?
Model Context Protocol is an open standard from Anthropic that lets AI clients read external context through a unified interface. BrainTube ships a native MCP server so any compliant client — Claude Desktop, Cursor, Zed — can query your library without bespoke integrations.
Which AI clients work with BrainTube today?
Any client that speaks MCP. That's the point of building on an open standard instead of one integration at a time — when a new assistant ships MCP support, it reaches your library without us shipping anything. Claude Desktop and Cursor are the ones walked through step by step below; ChatGPT support is in testing. Anything speaking MCP streamable-http uses the same endpoint and the same config.
Do I need to be on a paid plan to use the MCP server?
No. MCP access is included on every plan, including Free. What differs by tier is the BrainToken allowance: saving items, running searches and asking your brain all spend BrainTokens, and higher tiers get more of them. Free starts with 30 BrainTokens a month.
Where is my API key stored and how do I rotate it?
Keys are created in the BrainTube app under Settings → API Keys. They are shown once at creation, hashed at rest, and can be rotated or revoked at any time. Each key has its own audit log.
Can BrainTube read my private notes or only public videos?
BrainTube reads only what you save into your own library — public YouTube videos, articles you ingest, PDFs you upload. It never crawls third-party accounts on your behalf.
What happens to my data if I disconnect a client?
Disconnecting an MCP client removes its access. Your library, summaries, and highlights remain in BrainTube untouched. You can reconnect or export everything at any time.