@sid7vish/universal-rag-mcp
v3.2.1
Published
Universal RAG Memory MCP Server for AI assistants
Readme
Universal RAG MCP Server
A Model Context Protocol (MCP) server that provides persistent memory for AI assistants like Claude, ChatGPT, and others.
Features
- 🧠 Semantic Memory Search - Find relevant past conversations using natural language
- 💾 Persistent Storage - Memories persist across sessions via Supabase
- 🔌 Universal Compatibility - Works with Claude Desktop, Cursor, Windsurf, and any MCP-compatible client
- 📊 Memory Stats - Track your memory usage and activity
Available Tools
| Tool | Description |
|------|-------------|
| search_memory | Search past conversations and stored information |
| add_to_memory | Store new information, preferences, or facts |
| list_memories | List recent memories with metadata |
| get_memory | Get full details of a specific memory |
| delete_memory | Remove a memory by ID |
| get_memory_stats | Get statistics about stored memories |
Installation
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"ragmax": {
"command": "npx",
"args": ["-y", "@sid7vish/universal-rag-mcp", "start", "--api-key", "YOUR_API_KEY"]
}
}
}Cursor IDE
- Open Settings → Features → MCP
- Add new server with command:
npx -y @sid7vish/universal-rag-mcp start --api-key YOUR_API_KEYKiro IDE
Add to .kiro/settings/mcp.json:
{
"mcpServers": {
"ragmax": {
"command": "npx",
"args": ["-y", "@sid7vish/universal-rag-mcp", "start", "--api-key", "YOUR_API_KEY"]
}
}
}Get Your API Key
- Visit RAGMAX Dashboard
- Sign in and generate your API key
- Use the key in your MCP configuration
License
MIT
