# Tool Integration

A lightweight implementation of the MCP server that exposes custom tools via SSE for AI client integration.

This project guides you on how to build a client-host-server system based on the MCP protocol, including a FastAPI server, an MCP client, and an SSE streaming server. It enables the interaction of resources, tools, and prompts and supports integration with the Claude desktop application.

Portkey's Model Context Protocol (MCP) server implementation for connecting AI tools and services. Supports Docker, binary, and source code installation, provides SSE and stdio transport modes, and can be integrated with Cursor IDE and Claude Desktop.

Demonstration project for Claude desktop client configuration and tool integration

An MCP service implementation based on TypeScript, providing tool integration such as JIRA and TODO management

The MCP server is a service for processing the model context protocol. It supports installation through npm, yarn, or pnpm and provides examples of client calls.

A Model Context Protocol (MCP) implementation in Haskell, supporting interaction with clients such as Claude through StdIO and JSON-RPC, and providing resource, tool, and prompt management functions.

Flutter Inspector is an MCP server that connects Flutter applications with AI programming assistants, providing functions for debugging and inspecting Flutter applications.

Letta MCP Server is a model context protocol service implementation for interacting with the Letta API, providing agent management, memory block operations, and tool management functions.

This project provides a FastMCP server for batch execution of file and folder operations, including reading, creating, moving, deleting, etc., supporting centralized exception handling and batch tool calls.

The Letta MCP Server is a server toolset that provides agent management, memory operations, and Letta system integration.

This project demonstrates how to build a remote MCP server on Cloudflare Workers, including the OAuth login function, and supports connection and use through the MCP inspector and Claude desktop client.

JEBMCP is a project that combines JEB and MCP tools, aiming to simplify reverse engineering tasks through Python scripts and provide efficient code analysis and operation functions.

A modular server that implements the Model Context Protocol standard, providing integration of multiple tools and unified gateway access.

A modular server implementing the Model Context Protocol standard, providing integration of multiple tools such as GitHub, GitLab, Google Maps, memory storage, and Puppeteer web automation.

This project is an MCP server gateway hub used to centrally manage multiple MCP servers and integrate tool functions, avoiding repeated configuration and running of server processes for each LLM client. It supports dynamic configuration reloading and provides services for all managed servers and hub tools through a single interface.

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 into the Claude desktop application to call mathematical tools. Finally, a complete process for deploying to Cloudflare is provided.

This project implements the integration of the TypeScript MCP proxy with Ollama. Through a unified interface, AI models can call multiple tools, supporting functions such as file operations and web searches.

Documentation for the integration of the Unreal Engine Model Context Protocol (MCP), helping to understand, set up, and use the MCP system.

Cline's MCP protocol backend service, providing knowledge base integration and retrieval functions

A Model Context Protocol (MCP) tool for interacting with Polymarket via the Claude desktop application

MCP Ahrefs is an MCP server project based on the SAAGA framework, providing tool integration, exception handling, logging, and parallel processing functions, and supporting interactive testing through clients such as Claude.

The Kali MCP Server is an AI-driven network security testing platform that integrates over 55 professional security tools and supports multiple AI interfaces for intelligent penetration testing and vulnerability discovery.

This project implements a full-stack AI agent system inspired by the model context protocol, including a React front-end and a FastAPI back-end. The back-end serves as an AI coordinator, using Google Gemini to parse natural language instructions, safely call the file system, browser, or GitHub tools to perform tasks, and return the structured results to the front-end. The system focuses on software development scenarios, providing secure sandbox file operations, real-time web browsing, and repository inspection functions, and visualizing the tool call process.

Flux is an AI-based AO tool call enhancement system that enables AO code execution and custom blueprint creation through natural language, supports integration with existing AI development tools, and provides code testing functions.

A remote MCP server project based on Cloudflare Workers, supporting OAuth login and integrating with MCP Inspector and Claude desktop applications.

An API server based on the Model Context Protocol that provides authentication management and external API call functions, supporting secure token management and multiple response formats.

An MCP server implementation based on Ruby 3.3, providing greeting and calculation tools, supporting Cursor integration and background operation.

The MCP server is used to store and call programming rules, prompts, etc. on demand, helping developers share specifications across different projects and IDEs

MCP is an open-source AI-driven penetration testing framework that integrates multiple security tools, analyzes their outputs in real-time, strictly follows the standard penetration testing process, and provides intelligent assistance to security testers.