@t0ken.ai/memoryx-mcp-server 2.0.2 → 2.0.3

package/README.md

@@ -1,44 +1,28 @@
-# MemoryX MCP Server
+# 🧠 MemoryX MCP Server
 
-MemoryX MCP Server for Cursor, VS Code, Claude Desktop and other MCP clients.
+[![NPM version](https://badge.fury.io/js/@t0ken%2Fai%2Fmemoryx-mcp-server.svg)](https://www.npmjs.com/package/@t0ken.ai/memoryx-mcp-server)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-Powered by **@t0ken.ai/memoryx-sdk**
+**Give your AI assistants long-term memory via Model Context Protocol.**
 
-## Features
+MemoryX MCP Server enables Cursor, VS Code, Claude Desktop, and other MCP clients to store and retrieve memories across conversations.
 
-- **save_memory**: Save important information to memory system
-- **search_memory**: Search historical memories
-- **get_account_info**: Get account information
+## ✨ Features
 
-## Characteristics
+- 🚀 **Zero Config** - Auto-registers on first use, no API key needed
+- 🔍 **save_memory** - Store important information with automatic categorization
+- 🔎 **search_memory** - Semantic search across all historical memories  
+- ℹ️ **get_account_info** - Check connection status and agent info
 
-- Based on @t0ken.ai/memoryx-sdk
-- MCP mode: LLM summarizes and sends single memory additions
-- Server extracts entities directly without LLM summarization
-- Trigger: 20k tokens or 1 minute idle
-- Automatic retry mechanism
-- Offline support
+## 🚀 Quick Start
 
-## Installation
-
-### Option 1: NPM Install
+### Install
 
 ```bash
 npm install -g @t0ken.ai/memoryx-mcp-server
 ```
 
-### Option 2: Install from Source
-
-```bash
-cd plugins/memoryx-mcp-server
-npm install
-npm run build
-npm link
-```
-
-## Configuration
-
-### Cursor / VS Code
+### Configure Cursor / VS Code
 
 Add to `~/.cursor/mcp.json` or VS Code MCP config:
 
@@ -46,61 +30,101 @@ Add to `~/.cursor/mcp.json` or VS Code MCP config:
 {
   "mcpServers": {
     "memoryx": {
-      "command": "memoryx-mcp-server",
-      "env": {
-        "MEMORYX_API_KEY": "your_api_key_here",
-        "MEMORYX_URL": "https://t0ken.ai/api"
-      }
+      "command": "memoryx-mcp-server"
     }
   }
 }
 ```
 
-### Claude Desktop
+**That's it!** The server auto-registers on first use - no additional configuration needed.
 
-Add to Claude Desktop config file:
+### Configure Claude Desktop
 
 **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
+
 **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
 
 ```json
 {
   "mcpServers": {
     "memoryx": {
-      "command": "memoryx-mcp-server",
-      "env": {
-        "MEMORYX_API_KEY": "your_api_key_here"
-      }
+      "command": "memoryx-mcp-server"
     }
   }
 }
 ```
 
-## Usage
+## 📖 Tools
 
-### Auto Registration
+### save_memory
 
-If no API Key is provided, MCP Server will auto-register and generate one.
+Save information to long-term memory.
 
-### Manual Binding
+**When to call (automatic triggers):**
+1. User explicitly says "remember", "note this", "don't forget"
+2. User corrects your error (store the correct version)
+3. User expresses preferences (I like/hate/usually...)
+4. User mentions important experiences or future plans
+5. End of conversation - generate a 100-word summary
 
-1. Visit https://t0ken.ai/portal
-2. Login and copy API Key
-3. Configure environment variable `MEMORYX_API_KEY`
+**Categories (use in metadata.category):**
+- `semantic` - facts, knowledge, user preferences
+- `episodic` - specific events, experiences
+- `procedural` - skills, methods, how-to steps
+- `emotional` - feelings, emotional states
+- `reflective` - insights, patterns, lessons learned
 
-## Local Storage
+**Example:**
+```json
+{
+  "content": "User prefers dark theme in VS Code",
+  "metadata": {
+    "category": "semantic",
+    "tags": ["preference", "editor"]
+  }
+}
+```
+
+### search_memory
+
+Search historical memories before responding.
+
+**Always call BEFORE:**
+- Answering questions about user preferences/history
+- Topics that might relate to past conversations
+- Any personalized response needed
+
+**Workflow:** `search` → `review results` → `generate informed response`
 
-Data is stored in `~/.memoryx/mcp-server/` directory.
+### get_account_info
 
-## MCP Mode vs OpenClaw Conversation Mode
+Get current connection status including:
+- API Key (masked)
+- Agent ID
+- Queue length
+
+## 📁 Local Storage
+
+Data stored in `~/.memoryx/sdk/` (managed by SDK):
+- `memoryx.db` - SQLite database with agent info, queue, and cached data
+
+## 🔄 MCP Mode vs OpenClaw Mode
 
 | Feature | MCP Server | OpenClaw Plugin |
 |---------|------------|-----------------|
 | Data Source | LLM summarized single additions | Bidirectional conversation flow |
 | Server Processing | Direct entity extraction | LLM summarization then extraction |
-| Trigger Mechanism | 20k tokens / 1 min idle | 30k tokens / 5 min idle |
+| Trigger | 20k tokens / 1 min idle | 30k tokens / 5 min idle |
 | Use Case | Cursor/Claude Desktop | OpenClaw Gateway |
 
-## License
+## 📚 More Resources
+
+- [MemoryX Platform](https://t0ken.ai)
+- [Documentation](https://docs.t0ken.ai)
+- [Node.js SDK](https://www.npmjs.com/package/@t0ken.ai/memoryx-sdk)
+- [Python SDK](https://pypi.org/project/t0ken-memoryx/)
+- [GitHub](https://github.com/t0ken-ai/MemoryX)
+
+## 📄 License
 
-MIT
+MIT © MemoryX Team

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@t0ken.ai/memoryx-mcp-server",
-  "version": "2.0.2",
+  "version": "2.0.3",
   "description": "MemoryX MCP Server for Cursor/VS Code/Claude Desktop (powered by @t0ken.ai/memoryx-sdk)",
   "main": "dist/index.js",
   "bin": {