@mnemox/mcp-server-lite
Version:
MCP Server for MnemoX Lite - Semantic Memory for LLMs
213 lines (156 loc) โข 5.44 kB
Markdown
# @mnemox/mcp-server-lite
๐ง **MCP Server for MnemoX Lite v1.1.1** - Semantic Memory for LLMs via Model Context Protocol
Connect Claude Desktop (and other MCP-compatible LLMs) to your MnemoX Lite semantic memory system with native Google Cloud vector search.## ๐ Quick Start### 1. Run with NPX (Recommended)```bash# Interactive setup with auto-detectionnpx @mnemox/mcp-server-lite# Direct server mode npx @mnemox/mcp-server-lite --server```
### 2. Configure Claude Desktop
The setup wizard will generate a configuration like this for your `claude_desktop_config.json`:
```json
{
"mcpServers": {
"mnemox-lite": {
"command": "npx",
"args": ["mnemox-mcp-server", "--server"],
"env": {
"MNEMOX_API_URL": "http://localhost:3000/api/mcp",
"MNEMOX_API_KEY": "your-api-key",
"MNEMOX_USER_ID": "your-user-id"
}
}
}
}
```
### 3. Restart Claude Desktop
After adding the configuration, restart Claude Desktop. The MCP server will start automatically when you use Claude.
## ๐ ๏ธ Available Tools
Once connected, Claude will have access to these memory tools:
### `store_information`
Store information in semantic memory for future reference.
```
store_information({
content: "React hooks allow functional components to use state",
tags: ["react", "hooks", "frontend"],
source: "learning_session"
})
```
### `search_memory`
Search semantic memory for relevant information.
```
search_memory({
query: "React hooks state management",
maxResults: 10,
similarityThreshold: 0.7
})
```
### `relate_information`
Find information related to a specific memory fragment.
```
relate_information({
fragmentId: "fragment-123",
maxResults: 10
})
```
### `contextualize_information`
Organize information into thematic contexts.
```
contextualize_information({
query: "React development best practices",
createIfNotExists: true,
maxFragments: 50
})
```
### `get_memory_stats`
Get statistics about your semantic memory usage.
```
get_memory_stats()
```
## ๐ Configuration
### Environment Variables
- `MNEMOX_API_URL`: URL of your MnemoX Lite server (default: `http://localhost:3000/api/mcp`)
- `MNEMOX_API_KEY`: API key for authentication (default: `demo-key`)
- `MNEMOX_USER_ID`: User ID for memory operations (default: `demo-user`)
### Claude Desktop Config File Locations
- **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
- **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
## ๐งช Testing
Test the server manually:
```bash
# Start the MCP server
npx mnemox-mcp-server --server
# In another terminal, test with MCP client tools
# (Requires MCP development tools)
```
## ๐ง Development
### Local Installation
```bash
# Clone and install
git clone <repository>
cd mcp-server
npm install
# Run locally
npm start
```
### Package Structure
```
mcp-server/
โโโ bin/
โ โโโ mnemox-mcp # NPX executable
โโโ src/
โ โโโ server.js # MCP server implementation
โโโ package.json
โโโ README.md
```
## ๐ค Integration Examples
### Basic Memory Usage with Claude
```
Human: Remember that I prefer TypeScript over JavaScript for new projects.
Claude: I'll store that preference for you.
[Uses store_information tool]
โ
Information stored successfully!
Fragment ID: frag_abc123
Content: User prefers TypeScript over JavaScript for new projects
```
```
Human: What programming language should I use for my new web project?
Claude: Let me check your preferences first.
[Uses search_memory tool]
๐ Found 1 relevant memory:
1. [Score: 0.85] User prefers TypeScript over JavaScript for new projects
Based on your stored preference, I recommend using TypeScript for your new web project...
```
### Context Organization
```
Human: I've been learning about React hooks. Can you organize all my React knowledge?
Claude: I'll organize your React knowledge into a context.
[Uses contextualize_information tool]
๐ Context "React development knowledge" created with 15 fragments
Your React knowledge has been organized! This includes:
- React hooks concepts
- Component patterns
- State management
- Performance optimization tips
```
## ๐จ Troubleshooting
### Common Issues
**โ "API Error: 401 Unauthorized"**
- Check your `MNEMOX_API_KEY` in the configuration
- Ensure your MnemoX server is running and accepting the API key
**โ "Error calling MnemoX API: fetch failed"**
- Verify your `MNEMOX_API_URL` is correct
- Check that your MnemoX server is running on the specified URL
- Try accessing the health endpoint: `curl http://localhost:3000/api/mcp/health`
**โ "NPX package not found"**
- Ensure you have Node.js 18+ installed
- Try clearing NPX cache: `npx clear-npx-cache`
### Debug Mode
Enable verbose logging:
```bash
# Set debug environment variable
MNEMOX_DEBUG=1 npx mnemox-mcp-server --server
```
## ๐ Links
- [MnemoX Lite Documentation](https://github.com/mnemox/lite)
- [Model Context Protocol Specification](https://modelcontextprotocol.io/)
- [Claude Desktop](https://claude.ai/desktop)
## ๐ License
MIT License - see LICENSE file for details.
---
๐ง **Built with โค๏ธ by the MnemoX Team**