M

Memo

Verified Integration
Author: @jagoffCategory: ServerApplicationMIT
JSON-RPC 2.0
Protocol Standard
Sub-second
Execution Latency
Active
Operational Status

Client Configuration

— Connect Memo to Claude Desktop or Cursor in seconds
{
  "mcpServers": {
    "memo-2": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memo-2"
      ],
      "env": {}
    }
  }
}
Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).
Architecture & Capabilities

System Overview

Provides persistent semantic memory for AI agents, running entirely on Apple Silicon Macs with local storage and MLX-native processing.

Indexed Date

7/23/2026

License

MIT

Protocol Layer

stdio / SSE RPC

Frequently Asked Questions

Architecture and operational details for Memo

Memo requires macOS on Apple Silicon (M1/M2/M3/M4), Python ≥ 3.13, and approximately 4 GB of free disk space for the default MLX model set. An Obsidian vault is optional, as Memo can create a default vault for you.

Related MCP Servers

Browse all servers →
C
@carboneio
Carbone

Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.

ClaudeSearchDatabase+65 FAQs
Learn more
C
@sebastienrousseau
CloudCDN

Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.

ClaudeSearchDatabase+65 FAQs
Learn more

Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.

ClaudeSearchDatabase+55 FAQs
Learn more