Genkit is an open-source framework for building AI-driven applications, providing Node.js and Go libraries, supporting the integration of multiple AI models and vector databases, and including development tools and a plugin ecosystem.

Claude Context is an MCP plugin that provides in - depth context of the entire codebase for AI programming assistants through semantic code search. It supports multiple embedding models and vector databases to achieve efficient code retrieval.

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.

This project is a document processing server based on the Model Context Protocol (MCP) standard. By building a vector database and an MCP interface, it enables AI assistants to access external document resources and break through the knowledge limitations of large language models. The project includes two major components: a document processing pipeline and an MCP server. It supports multiple embedding models and file formats and can be applied to scenarios such as querying the latest technical documents and understanding private code libraries.

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.

Replicate Flux MCP is an advanced server based on the Model Context Protocol (MCP), which uses the Flux Schnell and Recraft V3 SVG models through the Replicate API to provide high-quality image and vector graphics generation capabilities for AI assistants.

The MCP Code Indexer is an intelligent code retrieval tool designed specifically for large AI language models. It improves the efficiency and accuracy of code processing through semantic understanding and vectorized indexing, supporting functions such as code analysis, quality assessment, and dependency management.

An MCP service for semantic search of Apple Notes, supporting local embedding models, full-text search, and vector storage.

A local vector database MCP server based on FAISS, providing document embedding, semantic search, and RAG functions, supporting multiple document formats and custom embedding models.

Brain Server is a knowledge embedding and vector search service based on the MCP protocol, providing high-quality text vectorization, semantic search, and knowledge management functions, supporting multiple embedding models and Docker deployment.

This is an experimental Observe MCP server project that provides API interaction capabilities with the Observe platform, including tools for executing OPAL queries, exporting worksheet data, and managing monitors. It enables semantic document search and troubleshooting manual recommendation through the Pinecone vector database, providing a secure data access bridge for technical LLM models.

VectorMCP is a Ruby library for implementing the server-side functions of the Model Context Protocol (MCP), enabling large language models (LLMs) to discover and interact with external tools, resources, and prompt templates.

A RAG system built with open-source embedding models, vector databases, and the Gemini large language model, supporting local document processing and dynamic index update.

The Storm MCP server is an open protocol that enables seamless integration of LLM applications with RAG data sources and tools, supports custom embedded models and vector database connections, and provides functions such as context sharing, tool systems, and file management.

Metis MCP Tools is a repository containing multiple toolkits, aiming to enhance the functions of Metis RAG applications. These tools provide functions such as database management, vector storage operations, document processing, and LLM interaction, and enable language models to interact with external resources through the standardized Model Context Protocol (MCP).

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.

VectorCode is a code repository indexing tool designed to optimize the prompt construction of large programming language models (LLMs) by indexing and providing code repository information. It supports multiple embedding engines, provides command - line tools and Neovim plugins to help developers more efficiently use project context to improve the quality of model output.