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.

An MCP server for obtaining and searching third - party software package documentation, supporting multi - source scraping, intelligent processing, and hybrid search.

A high - performance MCP server for semantic code search, written in Rust, supporting hybrid search (BM25 + vector embedding), AST intelligent chunking, and over 60 programming languages.

GraphRAG MCP is a hybrid retrieval system that combines the Neo4j graph database and the Qdrant vector database, providing document retrieval services that combine semantics and graph relationships for large language models.

The Malaysia Open Data MCP service provides convenient access to government datasets and collections, supporting enhanced unified search, Parquet file parsing, hybrid data access architecture, and multi - provider geocoding functions.

ClaudeHopper is an AI-based construction document assistance tool that enables intelligent interaction with construction drawings and specification documents through RAG and hybrid search technologies.

Edit-MCP is a model context protocol server integrated with the Microsoft Edit tool, providing advanced file editing capabilities for AI systems and adopting a hybrid architecture that combines direct file operations and Edit integration.

This is an MCP+RAG proof-of-concept project for the oil and gas industry. It automatically distributes user queries to the correct domain services (such as drilling, production, procurement, etc.) through intelligent routing and combines hybrid retrieval technology to obtain accurate information from documents, providing answers with references to achieve fast and unified access to cross-domain data.

A multi - functional document processing MCP server that supports scraping, processing, and intelligently retrieving third - party software package documentation from multiple sources, integrates the OpenRouter multi - model API, and provides hybrid search capabilities.

An MCP server that provides advanced reasoning capabilities for Claude in Cursor AI, including various reasoning methods such as Monte Carlo Tree Search, Beam Search, and Transformer Hybrid Reasoning.

A hybrid retrieval and navigation tool for RimWorld source code and XML definitions, combining lexical, semantic, and graph structures, supporting AI assistant calls

AmanMCP is a privacy-first, zero-configuration local code library retrieval-augmented generation (RAG) tool that integrates with Claude AI through the MCP protocol, providing hybrid search functionality. It runs entirely locally without the need for an internet connection.

An implementation of the MCP server based on iFlytek, supporting intelligent workflow scheduling and multi - model hybrid application architecture.

An MCP server based on LanceDB that enables LLMs to directly interact with local documents through proxy RAG and hybrid search.

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.

Flexible GraphRAG is a flexible platform that supports multi - data source document processing, automatic knowledge graph construction, hybrid search (full - text, vector, graph), and AI Q&A. It includes a FastAPI backend, an MCP server, and various front - end interfaces.

A Python toolkit for integrating Solr search through the MCP protocol, supporting hybrid search and vector optimization

MCPHub is a hybrid web/extension application for managing Model Context Protocol (MCP) servers, providing server management functions similar to apt/pip, including a modern web interface and secure local system integration.

The Meilisearch Hybrid Search MCP service provides a hybrid search function that combines keywords and semantic vectors.

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.

ClaudeHopper is an AI-driven building document assistant that enables direct interaction with building drawings and specifications through RAG and hybrid search technologies.

Apple RAG MCP is a retrieval-augmented generation system that provides Apple development expertise for AI agents. It integrates official Swift documentation, design guides, and Apple Developer YouTube content, and provides accurate technical answers through AI-driven hybrid search technology.

ctx-sys is a locally prioritized hybrid retrieval-augmented generation (RAG) tool designed for AI programming assistants. It analyzes the codebase through a tree parser, combines semantic vector search, keyword retrieval, and graph relationship traversal to provide in-depth project understanding for AI assistants. All operations are performed locally to protect code privacy.

A lightweight MCP server focused on crawling document websites and performing RAG indexing using Jina AI and Supabase, supporting multi - project management, intelligent URL discovery, and hybrid content extraction.

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.

A Q&A chatbot project about the EU AI Act, using a hybrid retrieval method (vector search + knowledge graph), providing local running and AWS Lambda deployment options.

This is a fast domain name availability checking server for the Model Context Protocol, supporting DNS and RDAP/WHOIS hybrid verification, batch checking, parallel processing, and automatic domain name expansion functions.

An MCP server for searching and browsing Claude conversation history, supporting hybrid search (full-text, Spotlight, and vector search), automatically reconstructs file paths and manages persistent indexes.

Edit-MCP is a model context protocol server integrated with Microsoft Edit tools, providing advanced file editing functions for AI systems. It uses a hybrid architecture that combines file system operations and Edit integration.

An MCP server for scraping and searching third-party package documentation, supporting asynchronous scraping, semantic chunking, vector embedding, and hybrid search 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.

The DPO2U MCP Platform is a hybrid AI compliance engine that combines local data processing with cloud - based legal knowledge, providing 17 tools to achieve 100% data localization processing and advanced compliance automation.

An MCP server that provides documentation and API references for the Niivue medical imaging library, supporting fast text search and optional semantic hybrid search.

The Build Vault MCP server transforms The Build Podcast into a searchable knowledge base. Through hybrid search technology that combines semantic similarity and full-text search, it provides AI insights into business ideas, frameworks, and product strategies.

A server based on the Model Context Protocol (MCP) for performing enrichment queries on provided observables (such as IP addresses, domain names, etc.) through third - party services (such as VirusTotal, HybridAnalysis, etc.). This project is currently only for development and testing, supports multiple observable types and third - party services, and uses environment variables to manage API keys for security.

ViperMCP is a hybrid expert visual question-answering server based on ViperGPT. It provides streamable MCP tools through FastMCP, supporting visual positioning, combined image Q&A, and image Q&A relying on external knowledge.

An MCP server for interacting with Croit Ceph clusters through REST APIs, supporting automatic token optimization, built-in filtering, and hybrid mode tool management, significantly reducing the number of tools and improving LLM performance.

The REAPER MCP Server is a project that exposes the functions of the REAPER Digital Audio Workstation through an API interface. It uses a Lua - Python hybrid architecture, supports file or socket communication methods, and provides 756 tools covering multiple areas of audio processing.