MCP Go is a server-side framework for the Model Context Protocol (MCP) implemented in Go, used to connect LLM applications with external data sources and tools. It provides core functions such as resource management, tool invocation, and prompt templates, and supports session management and middleware extension.

MCPEngine is a production-grade implementation of the Model Context Protocol (MCP), providing standardized interfaces for large language models (LLMs). It supports functions such as OAuth authentication, resource management, and tool invocation, aiming to become the 'REST of the LLM world' framework.

MCPGod is a command-line tool for quickly managing MCP servers, supporting client management, tool discovery and invocation, permission control, and detailed log recording.

The Dify plugin enables tool invocation through the MCP protocol and supports SSE and Streamable HTTP transport methods

The MCP Test Client is a middleware that serves both as a server for Claude and as a client for the server under test. It is used to test MCP servers during the development phase. It supports functions such as server deployment, tool invocation, test running, and log viewing, and provides a CLI interaction interface.

A proxy tool for centralized management of multiple MCP servers, supporting tool invocation forwarding and automatic discovery.

This project is a CSS teaching MCP server built on Node.js and TypeScript, providing personalized CSS feature update services, including resource management, tool invocation, and prompt guidance functions.

Hello-MCP is a simple project implementing the MCP protocol, including a client and a server, which helps understand the working principles of the MCP protocol.

This project demonstrates how to set up a remote MCP server on Cloudflare Workers, including OAuth login functionality, and supports connection and use through the MCP Inspector and Claude desktop client.

This project is a proof-of-concept (POC) that demonstrates how to implement the Model Context Protocol (MCP) through a custom host for testing agentic systems. Core features include OpenAI-compatible API, Google Gemini integration, streaming response support, and tool invocation capabilities.

A client project based on Python 3.13 that integrates MCP services and the GPT-4 model, providing interactive tool invocation and network search functionality.

This is a production-level medical agent server template based on the AOP protocol. It can deploy multiple professional medical agents as MCP tools, supporting the discovery and invocation of various medical analysis agents (such as laboratory data interpretation, ICD-10 coding, treatment plans, drug interactions, imaging triage, and clinical note summarization) through MCP clients, and providing functions such as queue management, dynamic discovery, and batch processing.

This project is a multi - tool integration and code execution platform based on FastMCP. It supports importing MCP tools from local and SSE clients, provides Docker deployment and streaming code execution management, and is suitable for various tool invocation scenarios such as chemical information query and web page parsing.

The MCP SSE proxy is an intermediate server that bridges the STDIO and SSE transport protocols, enabling MCP clients that only support STDIO to connect to remote SSE servers. It supports full MCP protocol functions, including tool invocation and resource access, and provides authentication, error handling, and logging functions.

An MCP protocol server implemented for the Replicate platform, providing model invocation and management tools

An offline IP Whois query tool that supports querying attribution information through IPv4 addresses and reverse searching for associated IP segments through keywords. It can be used for target asset collection and now integrates the MCP protocol for easy invocation by AI clients.

The MCP Agent Tool Adapter project enables modular tool invocation through the MCP protocol, supports two agent frameworks, Google ADK and LangGraph, and provides dynamic inference and tool planning capabilities.

A simple Kotlin weather query client-server example based on the MCP protocol, demonstrating the tool invocation process.

The MCP Server Unified Deployment Tool is a solution for standardized management of MCP servers deployed in various forms. It enables unified invocation through the SSE protocol and supports cross - platform and Docker containerized deployment.

This is an MCP server project that exposes the Restate Admin API through the MCP protocol as a tool, supporting basic functions such as management of service deployment, invocation operations, and state query.

Neva is an easily configurable MCP server and client SDK in Rust, supporting tool invocation and resource management. It is currently in the preview stage.

Mcpixir is an open - source Elixir library for connecting any LLM to the MCP server and building custom agents with tool access permissions. It supports multiple LLM providers and MCP servers, providing flexible tool invocation and server management functions.

The MCP Toolchain Server enables sequential invocation and result passing of multiple MCP tools

A supply chain AI optimization system based on a custom FastMCP implementation, processing real-time events through parallel invocation of multiple tools, providing inventory management, demand forecasting, and intelligent decision-making suggestions

This project includes custom slash commands for testing the integration of the Coroot MCP server, providing two testing methods: direct tool invocation testing and natural language testing, ensuring security and non-destructiveness.

A simple MCP server implementation based on TypeScript that supports SSE and STDIO transports, providing resource handling, prompting, and tool invocation functions.

This is an MCP server framework based on Ruby, implementing the Model Context Protocol (MCP), allowing large language models to invoke tools (such as generating random numbers). The project includes functions such as protocol processing, tool management, and logging, and supports integration with LLMs such as Claude.

A Python client for interacting with Model Context Protocol (MCP) endpoints via Server-Sent Events (SSE), supporting tool discovery, invocation, and integration with multiple LLMs.

This is an MCP server project that provides AT Protocol document query and key management functions for AI assistants such as Claude, supporting resource browsing and tool invocation.

The MCP DeepSeek demo project is a client application based on the MCP protocol, integrating DeepSeek AI to achieve tool invocation and real-time communication, including a Next.js front-end and an SSE server.

An HTTP Model Context Protocol (MCP) server based on Spring Boot, implemented using Spring AI, supporting OAuth2 authentication and tool invocation capabilities.

This project provides an MCP server that interacts with the Cisco APIC controller, supporting local invocation through Claude and VS Code, and includes functions such as APIC credential configuration, tool registration, and Docker support.

This is an example project that implements the MCP application extension specification, allowing the invocation of interactive HTML/JS user interfaces through MCP tools, including server - side and client - side demonstrations.

Develop an intelligent mall SSE service based on the MCP protocol, integrating product query, inventory management, and order processing functions, realizing real-time data interaction through the SSE protocol, and enhancing the shopping experience.

A lightweight Model Context Protocol (MCP) system based on FastAPI, including a server and a client, communicating through SSE and supporting tool invocation.

This project implements the Model Context Protocol (MCP), providing a modular framework for building MCP - compatible AI tool servers and clients, supporting tool registration, invocation, and standardized error handling.

MCP is a standardized protocol for interaction between AI models and applications, supporting tool invocation, resource management, and real-time data transfer.

This project demonstrates how to deploy a remote MCP server on Cloudflare Workers and implement OAuth login functionality. It supports local development and debugging, connection testing through the MCP inspector, and integration with the Claude desktop client to call MCP tool services.

This project demonstrates how to deploy a remote MCP server on Cloudflare Workers and implement the OAuth login function. The content includes local development, MCP inspector connection, Claude desktop application integration, and cloud deployment guides, supporting remote tool invocation through the SSE protocol.

This project demonstrates how to deploy a remote MCP server on Cloudflare Workers and implement OAuth login. It supports local development and debugging, connection testing through the MCP Inspector, and finally integrates with the Claude desktop application after deployment to Cloudflare for remote tool invocation.