Duckdb RAG MCP Sample
D

Duckdb RAG MCP Sample

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.
2.5 points
5.7K

What is the DuckDB RAG MCP Sample?

This is an example of a Retrieval Augmented Generation (RAG) system based on DuckDB and Plamo-Embedding-1B. It can convert markdown documents into vector form for storage and provide intelligent search functionality through the MCP protocol.

How to use the DuckDB RAG MCP Sample?

You need to first convert markdown documents into vector data, then configure the MCP server, and finally query through supported clients (such as Claude Desktop).

Applicable scenarios

Suitable for scenarios that require quickly searching a large amount of document content and obtaining relevant information, such as knowledge base Q&A and document retrieval.

Main features

Document vectorization
Extract and convert the content of markdown documents into vector representation
Vector search
Use DuckDB for efficient vector similarity search
Data persistence
Save and load vector data through the Parquet file format
MCP integration
Support providing search services through the Model Context Protocol
Advantages
A lightweight solution that does not require complex infrastructure based on DuckDB
Use the efficient Plamo-Embedding-1B model for vectorization
Support integration with multiple MCP clients
Data is stored in Parquet format, which is convenient for management and transmission
Limitations
Currently only supports markdown format documents
Need to manually convert documents into vector data
Performance may be limited by single-machine resources

How to use

Prepare documents
Put the markdown files to be searched into the specified directory
Generate vector data
Run the command to convert the documents into vectors and save them as a Parquet file
Build the server
Use PyInstaller to build a single-file executable server
Configure the MCP client
Configure the server path and parameters in the client (such as Claude Desktop)

Usage cases

Knowledge base Q&A
After vectorizing the company's internal knowledge base documents, obtain relevant information by asking natural language questions
Technical document search
Search for specific function descriptions in API documents

Frequently Asked Questions

Which document formats are supported?
How to update the search content?
Which MCP clients are supported?

Related resources

DuckDB official documentation
DuckDB database usage documentation
Introduction to Plamo-Embedding-1B
Technical blog about the vectorization model
MCP protocol description
Model Context Protocol specification

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

M
MCP
The Microsoft official MCP server provides search and access functions for the latest Microsoft technical documentation for AI assistants
8.7K
5 points
C
Cipher
Cipher is an open-source memory layer framework designed for programming AI agents. It integrates with various IDEs and AI coding assistants through the MCP protocol, providing core functions such as automatic memory generation, team memory sharing, and dual-system memory management.
TypeScript
0
5 points
A
Annas MCP
The MCP server and CLI tool of Anna's Archive are used to search for and download documents on the platform and support access through an API key.
Go
6.7K
4.5 points
S
Search1api
The Search1API MCP Server is a server based on the Model Context Protocol (MCP), providing search and crawling functions, and supporting multiple search services and tools.
TypeScript
14.6K
4 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
44.7K
4.3 points
B
Bing Search MCP
An MCP server for integrating Microsoft Bing Search API, supporting web page, news, and image search functions, providing network search capabilities for AI assistants.
Python
15.1K
4 points
A
Apple Notes MCP
A server that provides local Apple Notes database access for the Claude desktop client, supporting reading and searching of note content.
Python
12.6K
4.3 points
M
Modelcontextprotocol
Certified
This project is an implementation of an MCP server integrated with the Sonar API, providing real-time web search capabilities for Claude. It includes guides on system architecture, tool configuration, Docker deployment, and multi-platform integration.
TypeScript
13.6K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
16.6K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
14.8K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
24.5K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
44.7K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
20.2K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
44.3K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
30.2K
4.8 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
62.4K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIBase