MCP DuckDB Memory

v1.0.0Knowledge & Memorystable

MCP Memory Server with DuckDB backend

duckdbmcpmcp-servermodel-context-protocol
Share:
57
Stars
0
Downloads
0
Weekly
0/5

What is MCP DuckDB Memory?

MCP DuckDB Memory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp memory server with duckdb backend

MCP Memory Server with DuckDB backend

This server falls under the Knowledge & Memory and Databases categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP Memory Server with DuckDB backend

Use Cases

Store memory data using DuckDB backend.
Maintain context across sessions.
Query persistent conversation memory.
IzumiSy

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedMay 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-duckdb-memory

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP DuckDB Memory

MCP DuckDB Memory Server is a persistent, queryable knowledge graph memory backend for AI assistants that replaces the default JSON-file storage with a DuckDB embedded database. It stores entities (people, organizations, events), observations (facts about those entities), and relations (connections between them), and supports fuzzy search combining SQL queries with relevance ranking. Developers and power users who want their AI assistant to remember facts, preferences, and relationships across sessions — with better performance and richer query capabilities than flat JSON — use this server as a drop-in upgrade to standard MCP memory servers.

Prerequisites

  • Node.js 18 or later installed
  • npx available (ships with npm 5.2+)
  • An MCP-compatible client such as Claude Desktop
  • A writable directory path for the DuckDB memory file
  • Optional: Docker for a containerized deployment
1

Install via Smithery (recommended)

The easiest way to install is through the Smithery CLI, which automatically configures Claude Desktop for you.

npx -y @smithery/cli install @IzumiSy/mcp-duckdb-memory-server --client claude
2

Choose a path for the memory database

Decide where the DuckDB file should be stored. The file will persist your knowledge graph data between sessions. Use an absolute path in a location you control, such as your home directory.

mkdir -p ~/mcp-memory
# The file will be created at ~/mcp-memory/memory.data
3

Manually configure Claude Desktop (alternative to Smithery)

If you prefer manual setup, open claude_desktop_config.json and add the server entry below. The MEMORY_FILE_PATH env var controls where the DuckDB file lives; omit it to use a temporary in-memory store.

{
  "mcpServers": {
    "graph-memory": {
      "command": "npx",
      "args": ["-y", "@izumisy/mcp-duckdb-memory-server"],
      "env": {
        "MEMORY_FILE_PATH": "/Users/you/mcp-memory/memory.data"
      }
    }
  }
}
4

Restart Claude Desktop

Quit and relaunch Claude Desktop. The knowledge graph memory tools (for creating entities, adding observations, defining relations, and searching) should now appear in the tools panel.

5

Instruct Claude to use memory proactively

Add a system prompt or custom instruction telling Claude to search the knowledge graph at the start of each conversation and save new information at the end. This makes the memory useful in practice.

MCP DuckDB Memory Examples

Client configuration

Manual claude_desktop_config.json entry for the MCP DuckDB Memory Server with a persistent file path.

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

Prompts to try

Example prompts to build and query the DuckDB knowledge graph memory.

- "Remember that my colleague Sarah leads the infrastructure team and prefers async communication."
- "Search your memory for everything you know about the Project Phoenix initiative."
- "Create an entity for Acme Corp and record that they are a client in the retail sector."
- "What do you remember about my preferences for code reviews?"
- "Show me all the relations you have stored between people and projects."

Troubleshooting MCP DuckDB Memory

Memory is lost between Claude Desktop sessions

Confirm that MEMORY_FILE_PATH is set to an absolute path pointing to a writable directory. Without this env var the server uses an in-memory DuckDB instance that is discarded on exit. Check that the file actually exists and grows after a session.

npx hangs or throws an error when downloading the package

Try clearing the npx cache with npx clear-npx-cache and retrying. Alternatively pin a specific version: change -y @izumisy/mcp-duckdb-memory-server to -y @izumisy/mcp-duckdb-memory-server@latest and check npm registry for the current version.

Fuzzy search returns irrelevant results

The server combines SQL LIKE queries with relevance ranking. Use more specific entity names and observation text when storing facts. Very short or generic observations (e.g., 'likes things') degrade search quality significantly.

Frequently Asked Questions about MCP DuckDB Memory

What is MCP DuckDB Memory?

MCP DuckDB Memory is a Model Context Protocol (MCP) server that mcp memory server with duckdb backend It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP DuckDB Memory?

Follow the installation instructions on the MCP DuckDB Memory GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with MCP DuckDB Memory?

MCP DuckDB Memory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP DuckDB Memory free to use?

Yes, MCP DuckDB Memory is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-duckdb-memory": { "command": "npx", "args": ["-y", "mcp-duckdb-memory"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MCP DuckDB Memory?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides