MCP DuckDB Memory
MCP Memory Server with DuckDB backend
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
Maintainer
Works with
Installation
Manual Installation
npx mcp-duckdb-memoryConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
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
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 claudeChoose 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.dataManually 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"
}
}
}
}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.
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.
MCP DuckDB Memory Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to MCP DuckDB Memory? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
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.
Set Up MCP DuckDB Memory in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
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.