🧠 KacheDB MCP Server

High-Speed Model Context Protocol (MCP) server for KacheDB — exposing sub-millisecond in-memory caching and SIMD semantic vector memory to Antigravity IDE, Claude Desktop, Cursor, and AI coding agents.

⚡ Why KacheDB for AI Agents?

AI coding assistants (like Antigravity IDE and Claude Desktop) repeatedly re-read large codebases, AST parses, and architecture plans, wasting thousands of tokens and adding hundreds of milliseconds of latency per turn.

kachedb-mcp connects your AI assistant directly to KacheDB's Megaslab pure-RAM cache:

• 🚀 Sub-50 Microsecond Retrieval: $< 50\ \mu\text{s}$ cache hits in memory.
• 🧠 SIMD Semantic Vector Memory: Natural language concept and code recall powered by ARM NEON & AVX2/FMA cosine similarity kernels.
• 🪙 Massive Token & Cost Savings: Saves up to 80% of repetitive prompt tokens and tracks cumulative financial savings in real time.

🛠️ MCP Tools Exposed

🚀 Quickstart

1. Start the KacheDB Server Daemon

Ensure your KacheDB daemon is running locally:

kachedb-server --port 6379

2. Configure in Antigravity IDE / Claude Desktop / Cursor

Add kachedb to your MCP configuration file (mcp_config.json or claude_desktop_config.json):

{
  "mcpServers": {
    "kachedb": {
      "command": "uvx",
      "args": ["kachedb-mcp"],
      "env": {
        "KACHEDB_HOST": "127.0.0.1",
        "KACHEDB_PORT": "6379",
        "KACHEDB_INDEX": "agent_semantic_memory",
        "KACHEDB_THRESHOLD": "0.80"
      }
    }
  }
}

Or run via Python pip:

pip install kachedb-mcp

{
  "mcpServers": {
    "kachedb": {
      "command": "kachedb-mcp"
    }
  }
}

⚙️ Environment Configuration

📄 License

Licensed under either of Apache License, Version 2.0 or MIT License at your option.