This project demonstrates how to integrate the MCP (Model Context Protocol) server with Pydantic.AI, includes example code for weather services, and supports interaction through different LLMs (such as GPT - 4 and Sonnet).

The OpenRouter Agents MCP Server is a research agent server based on the Model Context Protocol (MCP). It uses Claude 3.7 Sonnet as the planning agent to coordinate multiple OpenRouter models to decompose and execute complex research tasks, providing efficient and reliable AI research services.

MCP MindMesh is a server that manages multiple Claude 3.7 Sonnet instances, achieving multi - agent collaboration through quantum - inspired swarm intelligence and generating highly consistent responses.

The GLM-4.6 MCP Server is an enterprise-level architecture consulting protocol bridging service that connects Claude 4.5 Sonnet and GLM-4.6 through the model context protocol, providing system design, scalability patterns, and technical decision-making support. It supports functions such as code architecture analysis, system architecture design, and decision review.

A development planning server based on the MCP protocol, integrating the ClaudeCode - DevPlanBuilder methodology into Claude Code. Through a workflow of structured interviews, detailed plan generation, Haiku execution, and Sonnet verification, it transforms ideas into executable development plans, including experience learning and GitHub issue fixing functions.