mcp-server-duckdb

MCP.Pizza Chef: ktanaka101

This connector hands your assistant a single tool: run any query against one DuckDB file on your computer. That covers reading, joining, creating tables, and pulling in CSV or Parquet files, because DuckDB accepts all of it through the same command. Nothing is sent to a cloud service and no account or key is needed. Writing is allowed by default; add the --readonly flag when setting it up and DuckDB itself blocks every change. Worth knowing before you commit: the code has not been touched since May 2025, though the repository is not archived.

Unmaintained · no commits since May 2025; not archived, no successor named
Data
Spreadsheets

Use This MCP server To

Ask questions about a CSV export without opening a spreadsheet Join two exported files and find the mismatched rows Count and group my records without writing the query Load a Parquet file and summarize what is inside Keep a small personal database my assistant can update Check one number in my data mid-conversation

README

mcp-server-duckdb

PyPI - Version PyPI - License smithery badge

A Model Context Protocol (MCP) server implementation for DuckDB, providing database interaction capabilities through MCP tools. It would be interesting to have LLM analyze it. DuckDB is suitable for local analysis.

mcp-server-duckdb MCP server

Overview

This server enables interaction with a DuckDB database through the Model Context Protocol, allowing for database operations like querying, table creation, and schema inspection.

Components

Resources

Currently, no custom resources are implemented.

Prompts

Currently, no custom prompts are implemented.

Tools

The server implements the following database interaction tool:

mcp-server-duckdb FAQ

Is this still being maintained?
It works, but the code has had no changes since May 2025 and the repository has been quiet since. It is not archived and the author names no replacement.
Do I need an account or a paid key?
No. Everything runs on your own machine against a database file you choose, and nothing is sent anywhere.
Can it change or delete my data?
Yes, by default. The one tool runs any statement it is given, including DROP and DELETE. Adding --readonly to the setup line blocks all writes, and DuckDB enforces that at the file level rather than by trusting the assistant.
Can I use this to analyze a CSV file?
Yes — DuckDB reads CSV and Parquet files directly, so you can point it at an export and ask questions about the contents.
How many tools does it add?
Exactly one, called query. The author deliberately chose a single general tool instead of several narrow ones.
Which apps does it work in?
Claude Desktop has documented steps for both Mac and Windows, and any MCP app that can launch a local command works. Smithery can install it for you.
How hard is it to set up?
You paste a short block into your settings with the path to your database file. The uv tool needs to be installed on your computer first.