DuckDB MCP server

The DuckDB MCP server enables interaction with DuckDB databases through the Model Context Protocol (MCP), allowing you to perform SQL operations like querying, creating tables, and analyzing data. This makes it possible to interact with databases directly in compatible MCP clients like Claude Desktop.

Installation

Using Smithery

The easiest way to install the DuckDB MCP server for Claude Desktop is via Smithery:

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

Manual Installation

You can also install the package directly using pip:

pip install mcp-server-duckdb

Configuring with Claude Desktop

To configure the MCP server in Claude Desktop, update the configuration file:

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

Windows: %APPDATA%/Claude/claude_desktop_config.json

Add the following configuration:

{
  "mcpServers": {
    "duckdb": {
      "command": "uvx",
      "args": [
        "mcp-server-duckdb",
        "--db-path",
        "~/mcp-server-duckdb/data/data.db"
      ]
    }
  }
}

Replace ~/mcp-server-duckdb/data/data.db with your preferred database file path.

Configuration Options

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

Optional Parameters

• --readonly: Run server in read-only mode (default: false)

  • Prevents any write operations on the database
  • Will not create the database file if it doesn't exist
  • Provides security by preventing the LLM from altering the database

• --keep-connection: Re-use a single DuckDB connection for the server lifetime (default: false)

  • Enables TEMP objects and slightly faster queries
  • Can hold an exclusive lock on the database file

Using the DuckDB MCP Server

The server provides a single tool:

Query Tool

The query tool allows you to execute any SQL statement on the DuckDB database:

• Input: Any valid DuckDB SQL statement as a string
• Output: Query results as text (or success message for operations like CREATE/INSERT)

Example Usage in Claude

Once the server is configured, you can interact with your DuckDB database through Claude by asking it to execute SQL queries:

Can you show me the tables in my DuckDB database?

Claude will use the query tool to execute:

SHOW TABLES;

You can also create tables, insert data, and perform complex queries:

Create a table called 'employees' with columns for id, name, and salary, then insert a few sample records.

Now show me the average salary from the employees table.

Working with Read-Only Mode

When the server is configured with the --readonly flag, Claude will be prevented from making any changes to your database. This is useful when you only want to analyze existing data without the risk of modification.

In read-only mode, operations like SELECT will work, but attempts to CREATE, INSERT, UPDATE, or DELETE will fail with an error message.

Practical Tips

• The server creates a new database file automatically if it doesn't exist (unless in read-only mode)
• For large databases, consider using read-only mode to prevent unintended modifications
• You can use all standard DuckDB SQL syntax for querying and data manipulation
• DuckDB supports many SQL operations similar to other database systems, with optimizations for analytical workloads

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "duckdb" '{"command":"uvx","args":["mcp-server-duckdb","--db-path","~/mcp-server-duckdb/data/data.db"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "duckdb": {
            "command": "uvx",
            "args": [
                "mcp-server-duckdb",
                "--db-path",
                "~/mcp-server-duckdb/data/data.db"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "duckdb": {
            "command": "uvx",
            "args": [
                "mcp-server-duckdb",
                "--db-path",
                "~/mcp-server-duckdb/data/data.db"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect