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 that provides any AI model with the ability to intelligently search for Claude Agent Skills through vector embeddings and semantic similarity, enabling progressive skill discovery and cross-platform skill sharing.

Mianshiya MCP Server is an interview question search service compatible with the MCP protocol. It is integrated through the Java SDK, supports multiple intelligent agent assistants to quickly access, and provides question retrieval functions.

The FHIR MCP Server is a medical data management server based on the FastMCP framework, providing a complete implementation of the Model Context Protocol (MCP) and supporting the interaction between LLM agents and FHIR-compatible backends. It provides standardized interfaces, supports comprehensive CRUD operations on FHIR resources, and implements intelligent document processing and semantic search through a series of tools.

BuildAutomata Memory is a persistent memory system based on the MCP protocol, providing semantic search and versioned memory storage across sessions for AI agents, supporting intelligent classification, timeline tracing, and multi-tool synchronization

A locally prioritized and agent-agnostic model context protocol server based on the Auggie SDK, providing codebase semantic search, file retrieval, intelligent planning, code review, and cross-session memory functions. It supports integration with multiple MCP clients.

Archive Agent is an intelligent file indexing tool that supports searching and querying file content through natural language. It combines AI search (RAG engine), automatic OCR, and the MCP interface, and can handle various file types, including text, documents, PDFs, and images.

TeaRAGs is a semantic code search MCP server designed for coding agents. It supports large - scale codebases through AST - aware chunking and incremental indexing, and uses Git trajectories (such as 19 signals including code changes, author information, and defect repair rates) for intelligent re - ranking, surpassing traditional embedding similarity retrieval.

DocNav is a document navigation server based on the MCP protocol, providing LLM agents with human - like document reading, analysis, and navigation capabilities, supporting multi - format document processing and intelligent search.

DomainKits MCP is a domain name intelligent agent framework designed for AI assistants. It integrates tools such as domain name search, analysis, monitoring, trend discovery, and batch processing, and can transform general - purpose AI assistants into professional domain name agents with industry - specific knowledge.

Fetch Browser is a powerful headless browser MCP server designed for AI agents, which can obtain web page content and perform Google searches without API keys. It supports multiple content format conversions and intelligent error handling.

DocNav is a document navigation server based on the MCP protocol, providing LLM agents with human-like long document reading, analysis, and navigation capabilities, supporting multi-format document processing and intelligent search functionality.

An intelligent research agent tool based on HuggingFace smolagents, providing advanced research functions such as web search and document analysis

The Unsplash Smart MCP Server is a professional image library integration solution designed for AI agents. It provides intelligent search, automatic attribution, and project-aware image management functions, simplifying the process of obtaining visual content for developers.

The MCP Development Agent is an intelligent development assistant based on the Model Context Protocol (MCP), providing memory management, document search, Git/GitHub integration, and code analysis functions. It supports CLI and SSE server modes and uses local AI models to achieve intelligent-assisted development.

Mianshiya MCP Server is an interview question search API service compatible with the MCP protocol, allowing intelligent agent assistants to quickly access and retrieve interview questions.

The BrianKnows MCP server is a protocol service that connects Claude to the blockchain knowledge base, providing functions such as API status detection, blockchain information search, and intelligent agent dialogue.

This project demonstrates how to combine the DuckDuckGo MCP server with the LangChain Groq LLM agent to achieve intelligent search functionality.

The Traylinx Search Engine MCP Server is a bridging service that connects to the Agentic Search API, allowing MCP clients (such as Claude and Cursor) to use intelligent search functions to obtain text summaries and structured data (HTML, images, etc.).

Intelligent product search system based on MCP service and OpenAI Agent SDK

This project demonstrates an intelligent agent based on LangChain, which integrates multiple service tools (search, weather, mathematical calculation) through the MCP protocol, adopts a modular design, and implements a perfect graceful shutdown mechanism.