# AI services

Explore the principle of the MCP architecture and practice building it, including the development of Client and Server components and the experimental process of connecting to LLM services

The Conversive AI project is a framework that provides core Gen AI services, aiming to support the Conversive platform. The project includes environment setup, dependency installation, configuration modification, and operation guides, as well as contribution specifications and contact information.

Cloudflare AI is a project containing various packages and demo applications for clients to consume Cloudflare AI services, managed using Nx and Changesets.

A simple MCP server based on Perplexity AI, providing web search functionality

An MCP server that provides image generation and web scraping functions for Windsurf, supporting image generation using the Flux Pro model and web content extraction through the ScrapeGraph API.

A Python template project for quickly building a Model Context Protocol (MCP) server, providing registration and exposure functions for tools and prompts, and supporting multiple deployment methods.

Obtain Taiwan weather data by connecting to the Central Weather Bureau API to provide accurate meteorological information for AI models

A GitHub repository Model Context Protocol (MCP) server based on the Python SDK, providing repository content access functions for AI assistants.

An implementation of the MCP server that supports OpenAI and Mistral, developed based on the Vercel AI SDK.

MCP Servers is a collection of servers and services for a Model Composition Platform (MCP), aiming to promote the integration and deployment of various AI/ML models and services. The project adopts a modular architecture, supporting standardized communication and scalable design, and includes various server types such as weather services.

An MCP server implementation based on the Cloudflare Flux 1 Schnell AI model, providing a service interface for text-to-image generation.

AI-friendly MCP server designed for Hacker News

FastMCP is a Python tool for quickly building MCP servers and clients, simplifying the implementation of standardized protocols for interacting with LLMs.