This project uses Playwright for automated browser testing and is integrated and deployed with Cloudflare Workers, Browser Rendering, and @cloudflare/playwright, supporting web page interaction operations through an AI assistant.

A serverless YouTube subtitle extraction service based on Cloudflare Workers, using the MCP protocol to achieve high - performance AI assistant integration

A lightweight Model Control Protocol (MCP) server based on Cloudflare Workers for AI agents to interact with the Vercel API

A Cloudflare Workers-based MCP server that uses the WebforAI library to extract plain text content from web pages and provides web page data for AI models.

An AI-driven research orchestration service based on Cloudflare Workers that provides comprehensive and structured research answers by intelligently analyzing queries, invoking multiple professional tools in parallel, and integrating the results.

MCP Workers AI is an SDK designed for Cloudflare Workers, used to integrate and call various MCP server tools, such as GitLab and Slack, to achieve automated operations through AI models.

This is a custom AI tool demonstration project based on Cloudflare Workers and the MCP protocol, which can be integrated with AI assistants such as Claude and Cursor to expand AI functions.

A WordPress Trac data MCP service developed in TypeScript, deployed on Cloudflare Workers, providing AI assistants with comprehensive access to WordPress development data and supporting standard MCP clients and ChatGPT Deep Research functions.

This is an MCP protocol demonstration project based on Cloudflare Workers and Remix 3, showing how to embed an interactive calculator widget in the AI chat interface. The project includes a complete MCP server implementation, state management, and widget communication system, and a hidden Easter egg in the TRON style is specially designed.

This is a full-stack application based on Cloudflare Workers that combines a React front-end, REST API, and MCP server functionality, using Stytch for user authentication. The project demonstrates how to extend a traditional application into a solution that supports AI agents.

The Crawl4AI MCP Server is a high-performance Model Context Protocol server that provides web scraping, crawling, and in-depth research functions for AI assistants. It is deployed via CloudFlare Workers and supports OAuth authentication and structured data extraction.

A Google MCP remote service based on Cloudflare Workers, providing Google API tools such as Gmail, Calendar, and Drive, enabling seamless integration with AI clients.

This project is an authentication-free remote MCP server deployed on Cloudflare Workers, providing website analysis and content extraction tools, leveraging Cloudflare's browser rendering and AI capabilities.

Build an MCP server using Cloudflare Workers to enable interaction between AI assistants and services

A remote MCP server project based on Cloudflare Workers, supporting OAuth login and integration with AI tools such as Claude

A PostgreSQL remote MCP service deployed via Cloudflare Workers, supporting connection and use from the Cloudflare AI Playground or local clients.

kivv is an automatic arXiv research paper discovery and AI intelligent summarization system, integrated with Claude Desktop via the MCP protocol, supporting multi - user, RSS subscription, and cost optimization, and built on Cloudflare Workers.

This project demonstrates how to deploy a remote MCP server without authentication on Cloudflare Workers, supporting connection and use of custom tools through clients such as AI Playground or Claude Desktop.

An unofficial Schwab MCP server implemented in TypeScript, serving as a bridge between AI assistants and the Schwab API, providing functions such as account management and market data query. It needs to be deployed on Cloudflare Workers by the user themselves.

This project demonstrates how to deploy an authentication-free remote MCP server on Cloudflare Workers, supporting the use of custom tools through clients such as AI Playground or Claude Desktop.