duckdb-mcp

richardwooding/duckdb-mcp

3.2

If you are the rightful owner of duckdb-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

MPC Server for DuckDB is a specialized server designed to facilitate secure multi-party computation (MPC) using the DuckDB database system.

The MPC Server for DuckDB is a cutting-edge solution that integrates the robust capabilities of DuckDB with the security and privacy features of multi-party computation (MPC). DuckDB is an in-process SQL OLAP database management system that is designed to be fast, reliable, and easy to use. By combining this with MPC, the server allows multiple parties to collaboratively compute functions over their inputs while keeping those inputs private. This is particularly useful in scenarios where data privacy is paramount, such as in financial services, healthcare, and collaborative data analysis across organizations. The server is designed to be highly efficient, leveraging DuckDB's in-memory processing capabilities to ensure that computations are performed swiftly and accurately. Additionally, it supports a wide range of SQL operations, making it versatile for various analytical tasks. The integration of MPC ensures that sensitive data is never exposed, providing peace of mind to users who require stringent data privacy measures.

Features

  • Secure Multi-Party Computation: Enables collaborative computation without exposing individual data inputs.
  • DuckDB Integration: Leverages DuckDB's fast and reliable in-memory processing for efficient data handling.
  • SQL Support: Supports a wide range of SQL operations for versatile data analysis.
  • Data Privacy: Ensures that sensitive data remains private and secure during computations.
  • Scalability: Designed to handle large datasets and complex computations efficiently.

Usages

local integration stdio

python
mcp.run(transport='stdio')  # Tools defined via @mcp.tool() decorator

local integration ide plugin

{
  "mcpServers": {
    "duckdb": {
      "command": "python",
      "args": ["duckdb.py"]
    }
  }
}

remote integration sse

python
mcp.run(transport='sse', host="0.0.0.0", port=8000)  # Specify SSE endpoint

remote integration streamable http

yaml
paths:
  /mcp:
    post:
      x-ms-agentic-protocol: mcp-streamable-1.0  # Copilot Studio integration

platform integration github

{"command": "docker", "args": ["run", "-e", "GITHUB_PERSONAL_ACCESS_TOKEN", "ghcr.io/github/github-mcp-server"]}

development framework fastmcp

python
from mcp.server import FastMCP
app = FastMCP('demo')
@app.tool()
async def query(): ...