Haiku RAG is an intelligent retrieval - augmented generation system built on LanceDB, Pydantic AI, and Docling. It supports hybrid search, re - ranking, Q&A agents, multi - agent research processes, and provides local - first document processing and MCP server integration.

A two-stage AI dialogue service that combines DeepSeek inference and Claude generation

An MCP server that provides framework documentation retrieval for Claude Code, supporting real - time document access, intelligent caching, and context enhancement features for over 85 frameworks.

This project implements an MCP server and client for building intelligent agent applications based on Retrieval Augmented Generation (RAG). The server provides tools such as entity extraction, query optimization, and relevance checking, and the client demonstrates how to connect to the server and use these tools to enhance the performance of the RAG system.

rag - mcp is an over - designed retrieval - augmented generation system that provides multiple text search modes (semantic search, question - answer search, style search) through a Python server. It uses PostgreSQL and pgvector to store text embedding vectors, supports interaction with AI agents, and has a complex but scalable architecture.

This project implements an MCP server based on the FAISS vector database, supporting the Retrieval Augmented Generation (RAG) function, including a complete workflow such as GitHub file download, document indexing, local query, and LLM integration.

A diary system based on Retrieval Augmented Generation (RAG), supporting diary organization by date and topic, and providing semantic search functionality, which can be connected to an AI agent to enhance interaction.

This project builds a Retrieval Augmented Generation (RAG) server based on IBM Watsonx.ai, uses ChromaDB for vector indexing, and exposes interfaces through the Model Context Protocol (MCP). The system can process PDF documents and answer questions based on the document content, realizing an intelligent question answering function that combines large language models with specific domain knowledge.

An unofficial UniProt MCP server that provides 26 bioinformatics tools, supporting advanced functions such as protein search, structural analysis, and functional annotation, and directly accessing the UniProt database through the REST API.

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.

An MCP server based on TypeScript that implements a Retrieval Augmented Generation (RAG) system for local documents, supporting querying and indexing of Git repositories and text files.

This is a demonstration project of a hybrid retrieval augmented generation (RAG) search system based on MariaDB Cloud. It integrates MariaDB vector search and Brave Search web search enhancement implemented through the FastMCP server, uses the 20 Newsgroups dataset as an example, and provides a plug-and-play hybrid search architecture.

mcp-rag-server is a service based on the Model Context Protocol (MCP) that supports Retrieval Augmented Generation (RAG) and can index documents and provide relevant context for large language models.

A Godot documentation query assistant based on Retrieval Augmented Generation (RAG), achieving intelligent Q&A through vectorization technology and semantic search.

A server based on the Model Context Protocol (MCP) that provides Retrieval Augmented Generation (RAG) capabilities, integrates clients such as Cursor IDE and Claude Desktop, and enables domain knowledge Q&A, intelligent retrieval, and context-aware response generation.

The Knowledge RAG System is a local retrieval - augmented generation system that integrates with Claude Code through the MCP protocol. It supports hybrid search (semantics + keywords) for multiple document formats such as PDF and Markdown, and provides keyword routing functions, suitable for personal knowledge base management.

MCP Apple Notes is a service based on the Model Context Protocol that can perform semantic search and Retrieval Augmented Generation (RAG) on Apple Notes, enabling AI assistants like Claude to reference users' notes in conversations.

An unofficial PubChem MCP server that provides comprehensive access to over 110 million compounds, including molecular properties, biological assay data, and cheminformatics tools.

An implementation of a Retrieval Augmented Generation (RAG) service based on the AWS knowledge base

The RAG Anything MCP Server is a Model Context Protocol server that provides comprehensive Retrieval Augmented Generation (RAG) capabilities. It supports multi-modal document processing and querying, and has functions such as end-to-end document parsing, batch processing, advanced querying, and persistent storage.

This project demonstrates how to implement a Model Context Protocol (MCP) server supporting Retrieval Augmented Generation (RAG), providing functions for knowledge base interaction, information retrieval, and document management.

RAG Vault is a locally prioritized document retrieval augmented generation tool that provides AI assistants with quick access to private documents through the MCP protocol. It supports multiple file formats, performs indexing and searching locally, ensures data privacy, and offers hybrid search, a Web interface, and a remote server mode.

An MCP server implemented for the OpenAI API, providing a standardized interface to connect Augment with OpenAI language models, supporting functions such as chat completion, model listing, and embedding generation.

mcp - rag - server is a Retrieval Augmented Generation (RAG) server based on the Model Context Protocol (MCP). It provides relevant context for connected LLMs by indexing project documents. It uses ChromaDB and Ollama for local storage and embedding generation, supports multiple file formats, and can be quickly deployed using Docker.

MiniRAG-MCP is an MCP server wrapper built around the MiniRAG project, aiming to provide efficient and reliable Retrieval Augmented Generation (RAG) services for intelligent agent processes on local devices through client-managed LLM inference sampling.

The R2R MCP Server is a service that integrates the Model Context Protocol (MCP) with the R2R system, providing interaction capabilities with MCP-compatible models such as Claude, and supporting functions such as knowledge base access, context search, and Retrieval Augmented Generation (RAG).

This project builds an AI system based on Nasdanika capabilities, focusing on operating on resource collections (interconnected models). It describes model elements and their relationships from multiple angles through the 'narrator' processor, and uses embeddings and vector storage to implement semantic search and RAG (Retrieval - Augmented Generation). It also supports the chat completion functions of OpenAI and Ollama.

This project is a RAG (Retrieval Augmented Generation) service based on the AWS serverless architecture. It uses Lambda, OpenSearch Serverless, and S3 for document storage and retrieval, provides an MCP protocol interface through API Gateway, and integrates OpenAI for embedding and generation.

An open - source project researching the integration of Retrieval Augmented Generation (RAG) with Multi - Cloud Processing (MCP) servers, focusing on the application of free models in business software and providing a modular learning path and practical cases.