Laravel Vibes is a powerful Laravel package for implementing the Machine Control Protocol (MCP) server, supporting seamless integration of AI agents. It provides features such as a tool registration system, real-time communication (SSE), and API endpoints, and supports automatic discovery and type safety.

The Propbar MCP Server provides UK property research tools, enabling AI assistants to search for properties, analyze area safety, find nearby schools, explore demographic data, and build an automated valuation model, covering data on over 30 million UK properties.

The Cloudflare MCP server is a modern model-context-protocol service that provides a structured tool interface for Cloudflare features such as DNS, security, redirection, and zone settings. It is compatible with AI clients like Claude Desktop, supporting plug-and-play and type safety.

The MCP server project for the US Data.gov public data portal encapsulates the public APIs of multiple US government agencies into standardized MCP servers, enabling AI tools to conveniently access public data such as census, financial regulation, drug safety, labor statistics, and environmental monitoring.

A collection of 46 professional AI sub - agents to expand the functionality of Claude Code, covering multiple fields such as development, architecture, language, infrastructure, quality and safety, data AI, etc., and achieving task optimization through specific model allocation.

The ATTOM MCP Server is a comprehensive model context protocol server that provides access to ATTOM real estate data for AI agents and traditional applications. It supports HTTP and stdio transmissions, and features intelligent fallback strategies, automatic retry mechanisms, and strict type safety.

The DeepRecall MCP server provides product safety intelligence services for AI agents through the model context protocol, and can search for over 120,000 product recall information from multiple global regulatory agencies.

PydanticAI is a Python agent framework developed by the Pydantic team, aiming to simplify the development of production-grade applications based on generative AI. It supports multiple AI models, integrates Pydantic validation and structured output, provides a dependency injection system, streaming responses, and graph support, and seamlessly integrates with Pydantic Logfire. It is suitable for building AI applications that require type safety and efficiency.