Second Brain
About
Self-hosted semantic memory layer for Claude and MCP-compatible AI clients. Store notes, search by meaning not keywords, and recall relevant context automatically. Built on Cloudflare Workers, D1, Vectorize, and Workers AI. Runs on the free tier. One-click deploy.
Details
- Author
- rahilp
- Downloads
- 532
- Categories
- Cloud Service, AI
Jump to
- Five tools: remember, recall, list_recent, forget, append
- Semantic vector search by meaning, not keywords
- Duplicate detection blocks near-exact matches before storage
- Long notes are automatically chunked before embedding
- Built on Cloudflare Workers, D1, Vectorize, and Workers AI
- Runs entirely on the free tier with one-click deploy
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Second BrainCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Deploy Second Brain with one click on Cloudflare’s free tier. Once deployed, it works with Claude Desktop, Claude Code, and claude.ai. No explicit installation commands or config keys are documented in the README.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"second brain": {
"second-brain": {
"command": "npx",
"args": [
"mcp-remote",
"https://<your-worker-url>/mcp"
]
}
}
}
}McpServers
{
"second-brain": {
"command": "npx",
"args": [
"mcp-remote",
"https://<your-worker-url>/mcp"
]
}
}A self-hosted memory layer for Claude and any MCP-compatible AI client. Gives your AI persistent, searchable memory across sessions using semantic search — not keywords.
Five tools:
1. remember — store a note with duplicate detection
2. recall — semantic vector search by meaning
3. list_recent — chronological listing by tag
4. forget — delete entry and all its chunks
5. append — update an existing entry with a timestamp
How it works:
Notes are embedded using bge-small-en-v1.5 on Workers AI and stored in Cloudflare Vectorize. Long notes are chunked before embedding so each section gets its own vector. Duplicate detection blocks near-exact matches before storing.
Stack: Cloudflare Workers, D1, Vectorize, Workers AI. Runs entirely on the free tier. One-click deploy provisions everything automatically.
Works with Claude Desktop, Claude Code, and claude.ai.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
