ktanaka101/mcp-server-duckdb

Overview

This is a Model Context Protocol server that enables LLM agents to interact with DuckDB databases. It exposes DuckDB's SQL capabilities through the MCP standard. Written in Python, it allows reading and querying data stored in DuckDB files or in-memory.

Best for

Best for
Developers building AI agents that need lightweight SQL querying on local or analytical datasets.

Use cases

• Run SQL queries on local or remote DuckDB files
• Integrate DuckDB analytics into LLM agent workflows
• Perform ad-hoc data analysis via natural language requests through MCP

How to use

Install

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

Tools exposed

• query

Tested with

Claude Desktop

Example client config

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

Notes

This is a Model Context Protocol server that enables LLM agents to interact with DuckDB databases. It exposes DuckDB’s SQL capabilities through the MCP standard. Written in Python, it allows reading and querying data stored in DuckDB files or in-memory.

176 stars on GitHub. Last updated 2025-05-05. Licensed MIT.

Use cases

• Run SQL queries on local or remote DuckDB files
• Integrate DuckDB analytics into LLM agent workflows
• Perform ad-hoc data analysis via natural language requests through MCP

Pros

• Leverages DuckDB’s fast, efficient query execution for analytical workloads
• Simple setup using standard MCP client libraries
• Supports both file-based and in-memory databases

Cons

• Limited to DuckDB; cannot query other database systems directly
• Requires Python runtime and MCP client setup
• Not optimized for high-concurrency production environments

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.