MCP Catalogs
Home

mcp-duckdb-memory-server

by IzumiSy·57·Score 46

A production-ready MCP memory server using DuckDB as backend for knowledge graph storage and retrieval.

knowledge-graphdeveloper-toolsai-llm
12
Forks
15
Open issues
1 mo ago
Last commit
2d ago
Indexed

Overview

This MCP server implements a memory system with a DuckDB backend, replacing the original JSON file-based storage. It provides a structured approach to storing and retrieving knowledge graph data including entities, observations, and relationships. The implementation combines SQL queries with Fuse.js for flexible entity searching, offering both structured queries and fuzzy matching capabilities. It maintains transaction integrity and supports indexing for better performance with large datasets.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Building persistent memory for AI assistants
you:Creating knowledge graphs for personal information management
you:Enhancing chatbot capabilities with relational data storage
you:What is the difference from the original memory server?
you:How does the fuzzy search work?

When to choose this

Choose this when you need a persistent, scalable memory system for AI applications with structured knowledge graphs and efficient search capabilities.

When NOT to choose this

Don't choose this if you need a simple in-memory solution for very small datasets or if you prefer JSON-based storage without external dependencies.

Comparable tools

mcp-knowledge-graph-memory-servervectordb-mcppostgres-mcp

Installation

Installation

Via Smithery

npx -y @smithery/cli install @IzumiSy/mcp-duckdb-memory-server --client claude

Manual Install

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "graph-memory": {
      "command": "npx",
      "args": [
        "-y",
        "@izumisy/mcp-duckdb-memory-server"
      ],
      "env": {
        "MEMORY_FILE_PATH": "/path/to/your/memory.data"
      }
    }
  }
}

Docker

docker build -t mcp-duckdb-graph-memory .
docker run -dit mcp-duckdb-graph-memory

FAQ

What is the difference from the original memory server?
This implementation replaces the JSON file backend with DuckDB, providing better performance, scalability, and query flexibility with SQL support.
How does the fuzzy search work?
The system combines DuckDB SQL queries with Fuse.js. SQL retrieves base data while Fuse.js provides fuzzy matching capabilities on top of the retrieved data.

Compare mcp-duckdb-memory-server with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.