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.

Airweave is an open - source context retrieval layer for AI agents and RAG systems. It connects and synchronizes data from various applications, tools, and databases, and provides relevant, real - time, multi - source contextual information to AI agents through a unified search interface.

MCP Agent Mail is a mail - based coordination layer designed for AI programming agents, providing identity management, message sending and receiving, file reservation, and search functions, supporting asynchronous collaboration and conflict avoidance among multiple agents.

An MCP server that connects agent systems to search systems through searXNG

Redis MCP Server is a natural language interface service designed for Redis, supporting AI agents to query and manage Redis data through natural language, integrating the MCP protocol, and providing multiple data structures and search functions.

MCP-Mem0 is a template implementation that provides long-term memory functions for AI agents, integrating the Model Context Protocol (MCP) server and Mem0, supporting memory storage, retrieval, and semantic search.

The Crawl4AI RAG MCP Server is an AI agent service integrating web crawler and RAG functions, supporting smart URL detection, recursive crawling, parallel processing, and vector search. It aims to provide powerful knowledge acquisition and retrieval capabilities for AI coding assistants.

An MCP server implemented for the RAG Web Browser Actor, supporting AI agents to perform web searches and content extraction.

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.

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.

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.

MCPfinder is a local server tool that provides dynamic capability expansion for AI agents. By searching for and installing toolkits compatible with the MCP protocol, language models can obtain new functions on demand.

MCP Gateway is a server aggregation tool that connects multiple Model Context Protocol (MCP) servers to a unified gateway. It exposes the tools of all connected servers through search, description, and invocation interfaces, effectively solving the problems of context overflow and cognitive overload caused by too many tool descriptions when connecting to multiple MCP servers.

markymark is a language server and AI agent tool for Markdown and structured data files, providing navigation, refactoring, search, and diagnostic functions, and supporting the LSP and MCP protocols.

o3 - search - mcp is an MCP server that supports using the OpenAI o3 model and its powerful web search function to help AI programming agents independently solve complex problems.

This project creates an AI agent based on the n8n platform that can discover and use Model Context Protocol (MCP) server tools through the Nostr network. The agent searches for available tools by querying Data Vending Machines (DVM) in the network, sends requests, and obtains responses, thereby expanding the functionality of the LLM to use MCP tools that are not installed.

Deep Research is an agent - based tool that provides web search and advanced research functions, supports PDF analysis, image description, and YouTube transcription extraction, and can run as an MCP server.

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

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.

An MCP server that connects to the Obsidian knowledge base. Through the REST API plugin, AI agents can perform complex knowledge discovery and analysis tasks, supporting functions such as advanced search, regular expression matching, and full - text retrieval.

A-MEM is a self-evolving memory system designed for coding agents. It uses a Zettelkasten-style knowledge graph structure, can automatically extract, associate, and evolve memories, supports semantic search and graph traversal, and integrates with agents such as Claude Code through the MCP protocol.

The PubMed MCP Server is an interface service based on the Model Context Protocol, providing comprehensive access to the PubMed biomedical literature database for AI agents and research tools. It supports functions such as literature search, metadata acquisition, citation analysis, research plan generation, and data visualization, and is efficiently integrated through the NCBI E - utilities API.

An MCP server for extending the context window/memory of AI agents, supporting the storage, retrieval, and management of memory content, including semantic search functionality.

OMEGA is a persistent memory system designed for AI programming agents, providing cross - session memory, semantic search, automatic capture, and task resumption functions. It is an open - source, local alternative to Mem0.

Agent Knowledge MCP is a comprehensive knowledge management solution that integrates Elasticsearch search, file operations, document validation, and version control functions, providing powerful knowledge management capabilities for AI assistants.

An MCP server that provides sandboxed file access, supporting directory exploration, file reading, content search, and secure editing, suitable for AI agents to manage text file collections.

An MCP server implementation that connects an AI agent with Google Flights data, supporting flight information query, cheapest option search, time filtering, and best recommendations.

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.

Codeix is a fast semantic code search tool designed for AI code assistants. By building a code index that can be committed to Git, it enables the search for symbols, references, and callers across codebases, improving the code location efficiency of AI agents.

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.

An autonomous AI research agent based on the MCP protocol, capable of completing the full research process such as web search, knowledge base retrieval, code writing, chart generation, and report writing through a single prompt.

Agent Knowledge MCP is a comprehensive knowledge management solution integrating Elasticsearch search, file operations, document validation, and version control functions, providing powerful knowledge management capabilities for AI assistants.

The ConsultingAgents MCP Server is a multi - model consulting agent server that provides four AI expert consulting services (Darren, Sonny, Sergey, Gemma) for Claude Code through the MCP protocol, supporting code analysis, document search, and repository - level development planning.

An OpenAI agent server based on the MCP protocol, providing various professional agents (such as web search, file search, and computer operation) and a multi-agent coordinator, which can interact with clients (such as the Claude desktop application) through the MCP protocol.

An advanced Obsidian MCP server that interacts with Obsidian through the Local REST API plugin, enabling AI agents to deeply understand the knowledge base structure, links, and content, and providing functions such as file operations, search, note management, and knowledge base analysis.

An MCP server for expanding the context window/memory of AI agents, supporting storage, retrieval, and management of memories, including semantic search functionality.

The Florentine.ai MCP Server allows AI agents to query MongoDB and MySQL databases through natural language, supporting functions such as multi - tenant data isolation, automatic schema exploration, and semantic vector search.

An MCP server based on Selenium WebDriver that allows AI agents to control browser sessions through the MCP protocol, enabling web automation operations such as navigation, element searching, and form filling.

The You.com DX Toolkit is an open-source AI development toolkit that includes npm packages, plugins, and skills, and can work in conjunction with more than 20 AI programming assistants such as Claude Code and Cursor. It provides tools such as the MCP server, Vercel AI SDK plugin, and Teams.ai integration, supporting real-time web search, AI agents, and content extraction functions.

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.