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:

  • query: Execute any SQL query on the DuckDB database
    • Input: query (string) - Any valid DuckDB SQL statement
    • Output: Query results as text (or success message for operations like CREATE/INSERT)

Note

The server provides a single unified query function rather than separate specialized functions, as modern LLMs can generate appropriate SQL for any database operation (SELECT, CREATE TABLE, JOIN, etc.) without requiring separate endpoints.

Note

When the server is running in readonly mode, DuckDB's native readonly protection is enforced. This ensures that the Language Model (LLM) cannot perform any write operations (CREATE, INSERT, UPDATE, DELETE), maintaining data integrity and preventing unintended changes.

Configuration

Required Parameters

  • db-path (string): Path to the DuckDB database file
    • The server will automatically create the database file and parent directories if they don't exist
    • If --readonly is specified and the database file doesn't exist, the server will fail to start with an error

Optional Parameters

  • --readonly: Run server in read-only mode (default: false)
    • Description: When this flag is set, the server operates in read-only mode. This means:
      • The DuckDB database will be opened with read_only=True, preventing any write operations.
      • If the specified database file does not exist, it will not be created.
      • Security Benefit: Prevents the Language Model (LLM) from performing any write operations, ensuring that the database remains unaltered.
    • Reference: For more details on read-only connections in DuckDB, see the DuckDB Python API documentation.
  • --keep-connection: Re-uses a single DuckDB connection mode (default: false)
    • Description: When this flag is set, Re-uses a single DuckDB connection for the entire server lifetime. Enables TEMP objects & slightly faster queries, but can hold an exclusive lock on the file.

Installation

Installing via Smithery

To install DuckDB Server for Claude Desktop automatically via Smithery:

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

Claude Desktop Integration

Configure the MCP server in Claude Desktop's configuration file:

MacOS

Location: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows

Location: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "duckdb": {
      "command": "uvx",
      "args": [
        "mcp-server-duckdb",
        "--db-path",
        "~/mcp-server-duckdb/data/data.db"
      ]
    }
  }
}
  • Note: ~/mcp-server-duckdb/data/data.db should be replaced with the actual path to the DuckDB database file.

Development

Prerequisites

  • Python with uv package manager
  • DuckDB Python package
  • MCP server dependencies

Debugging

Debugging MCP servers can be challenging due to their stdio-based communication. We recommend using the MCP Inspector for the best debugging experience.

Using MCP Inspector
  1. Install the inspector using npm:
npx @modelcontextprotocol/inspector uv --directory ~/codes/mcp-server-duckdb run mcp-server-duckdb --db-path ~/mcp-server-duckdb/data/data.db
  1. Open the provided URL in your browser to access the debugging interface

The inspector provides visibility into:

  • Request/response communication
  • Tool execution
  • Server state
  • Error messages

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.