Second Brain
Provides iOS shortcuts (Brain Dump, Text Brain Dump, Save to Brain) to capture memories from iPhone and iPad.
Syncs Notion pages shared with the integration into memory, with automatic nightly updates and on-demand sync.
Automatically syncs Obsidian notes into memory using the Second Brain Sync plugin.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Second Brainremember that the team meeting is at 3 PM"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Second Brain
One shared memory for Claude, ChatGPT, Cursor, Codex, and every other AI tool you use.
You use Claude for some things, ChatGPT for others, and Cursor for code. But your context, including your projects, decisions, and preferences, does not move with you. You end up explaining yourself again and again.
Second Brain gives every AI tool access to the same persistent memory.
Unlike memory built into a single app, this memory belongs to you. It runs in your own Cloudflare account, stays under your control, and cannot be locked inside one AI platform.
The easiest way to get started is the desktop app. It sets everything up for you in about two minutes — no terminal, no accounts to wire together, no technical steps.
⬇ Download for Mac or Windows
Prefer to run it yourself? Use the one-click Deploy to Cloudflare button, or follow the manual steps. See the Quick Start for all three options.
#3 Product of the Day on Product Hunt
Related MCP server: claude-recall
What's new in v2
Memory graph. Memories now connect to each other — automatically as you save, or explicitly with the new
linkandconnectionstools. Recall can follow those connections (thehopsoption) to surface related context that a plain search would miss, and the dashboard has a new Graph tab to explore your memory visually.Notion sync. Connect your Notion workspace from Settings → Integrations in the dashboard. Pages you share with the connection sync into memory, stay updated as they change in Notion, and surface in recall alongside everything else. Nightly automatic sync, or on demand with Sync now.
Graceful degradation. If the Vectorize index is missing, recall now falls back to keyword search with a clear notice instead of failing, a new
/healthendpoint reports index status, and the dashboard shows a banner with the exact fix.
See it in action

How it works
Connect Second Brain to the AI tools you already use, then save information as it comes up.
Second Brain retrieves memories by meaning rather than exact wording. Asking:
What did I decide about the pricing model?
can surface the correct memory even when the original note used completely different words.
Memory tools
Tool | What it does |
| Store ideas, decisions, preferences, and project context |
| Add an update to an existing memory |
| Replace an existing memory |
| Find memories by meaning rather than exact wording |
| Browse recently saved memories |
| Permanently delete a memory |
Save from anywhere
Memory is most useful when capturing information is easy. Second Brain connects to the tools and moments where context already exists.
AI clients: Use
rememberdirectly within Claude, ChatGPT, Cursor, Codex, and other MCP clients.Command line: Run
brain remember,brain recall, and other commands from your terminal.npm install -g second-brain-cf-cliNotion: Connect your Notion workspace from Settings → Integrations in the web dashboard. Create an internal connection in the Notion developer portal (a connection, not a personal access token — only connections appear in a page's Connections menu), share the pages you want remembered with it, and paste its secret — shared pages sync into memory automatically (nightly, or on demand with Sync now) and stay updated as they change in Notion.
Obsidian: Automatically sync notes using the Second Brain Sync plugin, also available through Obsidian Community Plugins.
Browser extension: Capture a page or highlighted text using the Chrome extension.
iPhone and iPad: Use the Brain Dump, Text Brain Dump, and Save to Brain shortcuts in
integrations/ios-shortcuts/.Bookmarklet: Use the lightweight bookmarklet in
integrations/bookmarklet.js.
Quick Start
Pick the option that fits you. They all deploy the same Second Brain into your own Cloudflare account — the difference is only how much setup you do by hand.
Option 1 — Desktop app (recommended, no technical steps)
The lowest-friction way to get started. Download the Second Brain desktop app for Mac or Windows, open it, and it walks you through setup in about two minutes: you pick a password, sign in to (or create) a free Cloudflare account, and it builds your Second Brain in your own private space and connects your AI tools for you. After setup it becomes the app you open your dashboard with every day.
Nothing to install beyond the app itself — no terminal, no git, no configuration values to copy. Developers: see installer/ for how it works and how to build it.
The Mac build is signed and notarized by Apple. The Windows build is not yet code-signed, so Windows may show a SmartScreen "unrecognized app" notice on first launch — click More info → Run anyway. (Code signing for Windows is in progress.)
Option 2 — One-click Cloudflare deploy
Prefer to deploy the Worker yourself without the app? Set it up in three steps.
1. Choose an authentication token
Your AUTH_TOKEN is the password used to access your Second Brain.
Use either:
A memorable phrase, such as
coffee-lover-2026A randomly generated token:
openssl rand -base64 32
Save this token somewhere secure. You will need it when authorizing clients and testing your deployment.
2. Deploy to Cloudflare
Click Deploy to Cloudflare and follow the prompts.
Enter the following values during setup:
FIELD | VALUE |
Dimensions |
|
Metric |
|
AUTH_TOKEN | The token you created in step 1 |
Cloudflare will provision the required resources and deploy your Worker automatically.
When deployment finishes, copy your Worker URL. It will look similar to:
https://your-worker-name.your-subdomain.workers.dev3. Connect your AI clients
Choose the instructions for the clients you use.
Claude Code or Codex CLI
Run the command for your operating system, replacing YOUR-WORKER-URL with the Worker URL from step 2.
macOS, Linux, WSL, or Git Bash
curl -fsSL https://raw.githubusercontent.com/rahilp/second-brain-cloudflare/main/scripts/connect-ai-clients.sh | bash -s -- https://YOUR-WORKER-URLWindows PowerShell
iex "& { $(irm https://raw.githubusercontent.com/rahilp/second-brain-cloudflare/main/scripts/connect-ai-clients.ps1) } -WorkerUrl https://YOUR-WORKER-URL"The setup script configures the MCP connection and global instructions using OAuth. Your authentication token is not passed to the script.
ChatGPT or Claude desktop and web apps
These clients require two manual setup steps:
Add the provided custom instructions to the app's personalization settings.
Add the following URL as a custom MCP connector:
https://YOUR-WORKER-URL/mcp
Follow the client-specific instructions in the wiki for the exact menus and settings.
Your Second Brain is now ready to use across every connected client.
Optional: Verify the deployment
Replace YOUR-WORKER-URL and YOUR-TOKEN with your own values:
curl -X POST https://YOUR-WORKER-URL/capture \
-H "Authorization: Bearer YOUR-TOKEN" \
-H "Content-Type: application/json" \
-d '{"content":"second brain is working","source":"test"}'A successful response will look like:
{"ok":true,"id":"..."}The /mcp endpoint supports OAuth 2.0 discovery and dynamic client registration.
When you add the following URL as an MCP connector:
https://YOUR-WORKER-URL/mcpa compatible client will:
Detect the authentication requirement.
Register itself with your Worker.
Open the hosted login page in your browser.
Ask you to enter your
AUTH_TOKEN.Store the resulting OAuth authorization.
This means your authentication token does not need to be placed in the client configuration or included in the connector URL.
The following clients support this flow:
ChatGPT
Claude.ai
Claude Code
Codex CLI
You can also configure supported command-line clients manually:
claude mcp add --transport http second-brain https://YOUR-WORKER-URL/mcpcodex mcp add second-brain --url https://YOUR-WORKER-URL/mcpClients that cannot open a browser, such as mcp-remote in a headless environment, can use static token authentication:
Authorization: Bearer YOUR-AUTH-TOKENOAuth requires the OAUTH_KV namespace for client registrations and tokens. The Deploy to Cloudflare button provisions it automatically.
Option 3 — Manual deployment
For developers who want full control from the command line. Requires Node.js and a Cloudflare account.
npm install
npm run vectors:create
npm run deploynpm run vectors:create creates the Vectorize index (384 dimensions, cosine). Wrangler then provisions the remaining Cloudflare resources automatically and fills in the required values in wrangler.jsonc. Then connect your AI clients using the same steps as Option 2, step 3.
Documentation
Setup Guide: Deploy the Worker, configure authentication, and connect AI clients
How It Works: Semantic search, chunking, memory classification, and duplicate detection
Connect to AI Clients: ChatGPT, Claude, Claude Code, Codex, and other MCP clients
Capture from Anywhere: Browser extension, bookmarklet, iOS Shortcuts, and share sheet
Web UI: Dashboard and mobile interface
Obsidian Plugin: Installation, configuration, and sync modes
API Reference: REST and MCP endpoints
Technology
Second Brain is built with:
Cloudflare Workers
D1 SQLite
Cloudflare Vectorize
Workers AI
Cloudflare KV
Model Context Protocol
TypeScript
It runs within Cloudflare's free tier at personal scale.
Your data stays in your own Cloudflare account.
Code signing policy
Windows builds of the Second Brain desktop app are code-signed.
Free code signing provided by SignPath.io, certificate by SignPath Foundation.
Team and roles:
Role | Members |
Authors | |
Reviewers | |
Approvers |
All release binaries are built from this repository's source by GitHub Actions (installer-release.yml). Every signing request is reviewed and manually approved by an approver before a signed release is published.
Privacy statement: This program will not transfer any information to other networked systems unless specifically requested by the user or the person installing or operating it. Second Brain is self-hosted by design: during setup the desktop app talks to Cloudflare only to create resources inside your own Cloudflare account, and afterwards it communicates exclusively with your own private Second Brain. Your memories and credentials are never sent to the project maintainers or any other third party.
Star History
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/LordCripto-Hub/mypeople-memory-cloudflare'
If you have feedback or need assistance with the MCP directory API, please join our Discord server