MCP DuckDB Knowledge Graph Memory Server

Name: MCP DuckDB Knowledge Graph Memory Server
Author: IzumiSy

@IzumiSy

Repository Homepage

About MCP DuckDB Knowledge Graph Memory Server

MCP Memory Server with DuckDB backend

#mcp #duckdb #model-context-protocol #mcp-server

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-duckdb-memory-server": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@IzumiSy/mcp-duckdb-memory-server",
        "--client",
        "claude"
      ]
    }
  }
}

Tools

No tools detected

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is MCP DuckDB Knowledge Graph Memory Server?

It is a forked version of the official MCP Knowledge Graph Memory Server that replaces the JSON file backend with DuckDB, a fast embedded analytical database. It stores a knowledge graph of entities, observations, and relations, and provides memory retrieval and update capabilities for AI assistants like Claude.

How to use MCP DuckDB Knowledge Graph Memory Server?

Install via Smithery (npx -y @smithery/cli install @IzumiSy/mcp-duckdb-memory-server --client claude) or manually add it to your claude_desktop_config.json with the command npx -y @izumisy/mcp-duckdb-memory-server and optionally set the MEMORY_FILE_PATH environment variable to a DuckDB database file. Use the provided instruction prompt to guide the AI on memory retrieval and updates.

Key features of MCP DuckDB Knowledge Graph Memory Server

Uses DuckDB as embedded analytical database
SQL interface for complex queries
Fuzzy search with Fuse.js integration
Transaction support for

Comments

Basic information

More Memory & Knowledge MCP servers

Obsidian MCP Server

StevenStavrakis

A simple MCP server for Obsidian

717

minutes

silverstein

Every meeting, every idea, every voice note — searchable by your AI. Open-source, privacy-first conversation memory layer.

1.3K

Orcha

westonhancock

Orcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age

The Cloud

Teka

The Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your

Memory

modelcontextprotocol

Model Context Protocol Servers

88.1K