JamesANZ/memory-mcp

> **Persistent memory and context window caching for LLM conversations.** Save, retrieve, and manage memories with intelligent context archiving. MongoDB-backed storage.
An MCP (Model Context Protocol) server that provides memory management and context window caching for AI coding environments like Cursor and Claude Desktop.
Why Use Memory MCP?
- 💾 **Persistent Storage** – MongoDB-backed memory that survives sessions
- 🧠 **Context Caching** – Intelligent archiving and retrieval of conversation context
- 🏷️ **Tag-based Search** – Organize and find memories by tags
- 📊 **Relevance Scoring** – Automatically score archived content relevance
- ⚡ **Easy Setup** – One-click install in Cursor or simple manual setup
Quick Start
Ready to add memory to your AI workflow? Install in seconds:
**Install in Cursor (Recommended):**
🔗 Install in Cursor
**Or install manually:**
Features
Basic Memory Tools
- **save-memories** – Save memories to database (overwrites existing)
- **get-memories** – Retrieve all stored memories
- **add-memories** – Append new memories without overwriting
- **clear-memories** – Remove all stored memories
Context Window Caching
- **archive-context** – Archive conversation context with tags
- **retrieve-context** – Retrieve relevant archived context
- **score-relevance** – Score archived content relevance
- **create-summary** – Create summaries of archived content
- **get-conversation-summaries** – Get all summaries for a conversation
- **search-context-by-tags** – Search archived content by tags
Installation
Cursor (One-Click)
Click the install link above or use:
Manual Installation
**Requirements:** Node.js 18+, npm, MongoDB
Claude Desktop
Add to claude_desktop_config.json:
**macOS**: ~/Library/Application Support/Claude/claude_desktop_config.json
**Windows**: %APPDATA%\Claude\claude_desktop_config.json
Restart Claude Desktop after configuration.
Configuration
Set the MongoDB connection string:
Default: mongodb://localhost:27017
Usage Examples
Save Memories
Store memories from a conversation:
Retrieve Memories
Get all stored memories:
Archive Context
Archive conversation context when it gets too long:
Retrieve Relevant Context
Get archived content relevant to current conversation:
Context Window Caching
The system automatically:
- **Archives content** when context usage reaches 80%
- **Retrieves relevant content** when usage drops below 30%
- **Scores relevance** using keyword overlap
- **Creates summaries** to condense long conversations
Use Cases
- **Long Conversations** – Manage context windows for extended sessions
- **Memory Persistence** – Save important information across sessions