# AI Tools

This project demonstrates how to deploy a remote MCP server on Cloudflare Workers and implement the OAuth login function, supporting connection and use through the MCP checker and Claude desktop client.

CodeBox-AI is a secure Python code execution service that provides self-hosted code interpreter functionality, supports conversational code execution, dynamic package installation, and visual output, and integrates the MCP protocol for interaction with LLM applications.

This project builds a lightweight MCP server that enables interaction between local AI tools and the Claude assistant through Python. It supports processing data files such as CSV and Parquet, facilitating natural language query and analysis.

A NestJS module for easily exposing AI tools, resources, and prompts via the Model Context Protocol (MCP), supporting multiple transport types and automatic discovery and registration functions.

LetzAI MCP is a model context protocol for image generation. Integrated through the Claude desktop application, it supports generating and upscaling images based on prompts.

A server based on the Model Context Protocol (MCP) and Server-Sent Events (SSE), integrating the Brave Search API to provide real-time streaming search functionality for AI models and clients.

A Python template project for quickly building a Model Context Protocol (MCP) server, which provides registration and exposure functions for tools and tips and supports multiple deployment methods.

Fujitsu's MCP server project for MAS development

The PubMed MCP Server is an interface service based on the Model Context Protocol, providing comprehensive access to the PubMed biomedical literature database for AI agents and research tools. It supports functions such as literature search, metadata acquisition, citation analysis, research plan generation, and data visualization, and is efficiently integrated through the NCBI E - utilities API.

An MCP server that connects to the Pounding The Rock RSS feed, providing AI assistant access to the latest game results and blog articles of the Spurs

Scraper.is MCP is a web scraping tool integration package based on the Model Context Protocol, enabling AI assistants to access the latest web content through the MCP protocol.

An intelligent chatbot based on Streamlit that uses GPT-4o to automatically route user requests to different tools (such as chatting, image generation, database queries, voice synthesis, etc.), supporting rapid experimentation with AI tool routing functions.

The combination of Gemini CLI and the MCP server built with Google Apps Script extends the automation capabilities of Google Workspace through a low - code platform, providing support for 41 tools covering services such as Gmail, Drive, Calendar, etc., and enabling multi - step execution of complex tasks.

An MCP service that connects to the Giphy API, providing GIF search, random retrieval, and trending content functions for AI models.

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

Vibe Coder is an MCP server that provides powerful software development tools for AI assistants, including code generation, research, planning, and project scaffolding functions.

The LangChain MCP client is a project that demonstrates how to use MCP server tools through the LangChain ReAct agent. It supports flexible selection of LLM models and enables dynamic interaction via the CLI.

This project demonstrates how to deploy a remote MCP server on Cloudflare Workers and implement the OAuth login function, supporting connection and use through the MCP Inspector and the Claude desktop client.

The Filesystem MCP Server is a Node.js-based filesystem tool server that follows the Model Context Protocol (MCP), providing AI agents with secure and efficient file access capabilities. It ensures operation security by limiting the project root directory, supports batch operations to reduce communication overhead, and offers rich file management functions such as reading, writing, editing, searching, and permission management.

An AI demonstration project showcasing the functions of the GitHub MCP server

MCP-hfspace is a server tool that simplifies the connection to Hugging Face Spaces. It supports multiple AI functions such as image generation, speech processing, and vision models, and seamlessly integrates with Claude Desktop.

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

Awesome MCP Servers is a curated list of Model Context Protocol (MCP) servers and tools. MCP is an open standard introduced by Anthropic that enables AI models to connect to external data sources and tools through standardized interfaces, enhancing their capabilities.

An MCP server for sending SMS via the Twilio API, integrating AI and status callback functions

An MCP client for interacting with the Notion API, supporting asynchronous operations, concurrency control, and environment configuration, which can be integrated into AI tools to expand functionality.

The OpenAI WebSearch MCP Server provides web search functionality for AI assistants through the Model Context Protocol, supporting the acquisition of the latest information during conversations.

The Edge Delta MCP Server is a server based on the Model Context Protocol, used for seamless integration with the Edge Delta API, enabling developers to build automation tools and AI applications to analyze observational data.

An MCP server that provides screen - capturing functionality, supporting AI tools to capture and process screen content.

This project demonstrates how to deploy a remote MCP server on Cloudflare Workers, including the entire process of local development, MCP inspector connection, Claude desktop application integration, and cloud deployment.

This project demonstrates how to deploy a remote MCP server on Cloudflare Workers and implement OAuth login functionality. It supports local development and debugging, and the service can be connected via the MCP inspector or the Claude desktop application, and finally deployed to the Cloudflare cloud.