# AI agent

Demonstrate connecting the Keboola Registry API to the MCP server through the CrewAI wrapper, enabling AI agents to call registered skills.

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.

This project demonstrates how to integrate OpenAI, Azure OpenAI, and GitHub models through the MCP protocol to build a terminal application for a TODO list agent. The project includes three major components: MCP host, client, and server, supports HTTP and SSE protocols, and provides tool invocation and database storage functions.

An MCP server for GitLab and Jira integration, providing functions for AI agents to interact with GitLab and Jira instances, including project management, merge request processing, file viewing, user activity tracking, and Jira ticket management.

Omni-LPR is a self-hosted server with multiple interfaces (REST and MCP) that provides automatic license plate recognition (ALPR) functions and can be used as an independent microservice or a toolbox for AI agents.

Xcatcher is a high - performance X (Twitter) data scraping service based on the remote MCP protocol. It supports pay - as - you - go with USDC on the Base and Solana chains via the x402 protocol, provides OpenAPI specifications for easy integration of AI agents, and focuses on the rapid collection of the latest posts of a large number of users.

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.

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.

A stateful Bluetooth Low Energy (BLE) Model Context Protocol (MCP) server that provides development tools and AI agents with the ability to interact with real BLE hardware. It supports operations such as scanning, connecting, reading and writing, and subscribing to notifications, and can extend device protocol specifications and plugins.

An AI-driven browser automation server based on the MCP protocol, supporting natural language control of web page operations and in-depth web research.

AnalyticDB for MySQL MCP Server is a universal interface service that connects AI agents and AnalyticDB for MySQL databases, supporting metadata retrieval and SQL operation execution.

A Gmail email management server based on the Model Context Protocol (MCP), supporting searching, reading, deleting, and sending emails through an AI agent. It needs to be used with a voice interaction client.

An example project that includes various AI agents and RAG technologies, covering Gemini applications, MCP services, Flutter applications, and Vertex AI integration, providing AI development examples from basic to advanced.

A high-performance PostgreSQL MCP server based on Bun and TypeScript, providing multi-database interaction capabilities for AI agents.

Flex MCP Agent is a multi - functional agent project that integrates weather data acquisition, Confluence interaction, and email sending functions, standardizing the interaction between AI models and data sources using the Model Context Protocol (MCP).

This project demonstrates how to integrate an AI agent powered by Azure OpenAI with the Microsoft Fabric data warehouse through the Model Context Protocol (MCP), using GraphQL as a common data connection layer to achieve bidirectional access to enterprise data.

AI code review and issue repair agent for analyzing codebases, detecting security vulnerabilities, reviewing code quality, and providing repair suggestions based on Sentry error logs.

An MCP server that supports Claude for API testing, providing general API testing and OpenAI - specific tools

MCP BatchIt is a batching server for MCP tool calls. By aggregating multiple MCP tool calls into one request, it significantly reduces the communication overhead and token consumption of AI agents.

The Agentic MCP Client is an independent AI agent runner that interacts with models such as Claude, BedRock, and OpenAI through MCP protocol tools, supporting autonomous cloud operation and secure system interaction.

An MCP server implementation for AdGuard Home, supporting querying and managing DNS records, filtering rules, etc. through an AI agent.

mcp - agent is a lightweight AI agent framework based on the Model Context Protocol (MCP), which supports building efficient agent applications through a simple and composable model. It integrates the lifecycle management of the MCP server and implements multiple workflow models, such as parallel processing, routing, evaluation optimization, etc., and is suitable for various AI application scenarios such as multi - agent collaboration and human - machine interaction.

Filesystem MCP is a Node.js-based Model Context Protocol server that provides secure, relative-path file system access services for AI agents (such as Cline and Claude).

PG-MCP is a model context protocol server designed for PostgreSQL databases, providing APIs for AI agents to discover, connect, query, and understand databases. It supports multi - database connection, rich catalog information, and query explanation functions.

Graphiti MCP Pro is a memory storage MCP service and management platform enhanced based on the Graphiti framework, providing asynchronous parallel processing, task management tools, unified configuration management, broader AI model compatibility, and a comprehensive visual management system.

Discourse MCP is a Model Context Protocol server that exposes Discourse forum functions as tools to AI agents. It supports operations such as searching, reading posts, and creating posts, provides read-only and writable modes, and supports remote tool discovery and dynamic registration.

Sequential Thinking MCP is an MCP server that supports AI agents in advanced metacognition and dynamic reflective problem-solving, guiding the step-by-step execution of complex tasks through virtual thought recording and planning.

BoostSecurity MCP is a security tool for protecting the AI agent development workflow. It prevents supply chain attacks by verifying the security of third - party software packages and supports multiple programming languages and package ecosystems.

PraisonAI is a production-ready multi-AI agent framework with self-reflection capabilities, designed to create AI agents to automate the solution of various problems from simple tasks to complex challenges. It simplifies the construction and management of multi-agent LLM systems by integrating PraisonAI agents, AG2, and CrewAI into a low-code solution, emphasizing simplicity, customization, and effective human-machine collaboration.

An MCP server based on pykrx, providing Korean stock market data query functions for AI agents, supporting multi - dimensional analysis of stock prices, financial indicators, investor transactions, short - selling data, etc.