An MCP server for querying Apple Health data via SQL, implemented based on DuckDB for efficient analysis, supporting natural language queries and automatic report generation.

An implementation of the MCP protocol interaction service for the DuckDB database

An MCP server that integrates MotherDuck and local DuckDB, providing SQL analysis capabilities for Claude

DuckDB MCP Server is a service that implements the Model Context Protocol (MCP), enabling AI assistants to interact with the DuckDB database via SQL, supporting queries from multiple data sources and cloud storage access.

A database service project based on the mcp - framework, providing tools for interaction between PostgreSQL and Google Cloud Storage

A Python-based document processing and Retrieval Augmented Generation (RAG) server that uses the DuckDB database to store embedding vectors, supports multiple file format processing, and provides a Web interface and API.

dank-mcp is a server based on the Model Context Protocol (MCP), specifically designed to answer questions about cannabis datasets. It stores and processes data through DuckDB, supports integration with LLM tools such as Claude Desktop, and provides a query service for cannabis product information for educational purposes.

A project that uses DuckDB and Plamo-Embedding-1B to implement RAG functionality, supporting vectorized storage and retrieval of markdown files and providing an MCP service interface.

This project designs and implements an architecture that connects the data space with generative AI. Through the Model Context Protocol (MCP) server as a secure middle layer, the language model can indirectly access the DuckDB database. It has the characteristics of modularity, extensibility, and log tracking, laying the foundation for future upgrades to the RAG architecture.

An MCP server implementation based on DuckDB, providing the ability to interact with the database through MCP tools, supporting operations such as queries, table creation, and schema inspection, and can be configured in read-only mode to ensure data security.

A modern data stack implementation based on Meltano, DuckDB, and dbt Core, including the full process of data extraction, loading, transformation, and validation, and integrated with the Claude Code MCP intelligent assistance service.

A powerful MCP server for Parquet file processing, offering functions such as text embedding generation, file analysis, DuckDB/PostgreSQL conversion, and Markdown processing

An MCP server that serves MotherDuck and local DuckDB, supporting connection initialization, schema reading, and query execution functions.

This project implements a Microsoft Teams message bridging service based on the MCP protocol, integrating PostgreSQL information retrieval and DuckDB storage, and supporting hybrid search and real-time event streaming.

Engram is an event - sourcing memory system designed for AI agents, adopting an architecture without an LLM write path, and achieving reliable semantic search memory storage through local vector embeddings and DuckDB.