This project demonstrates how to use the OAuth 2.1 authorization process and AWS Cognito to protect MCP servers, including the implementation of core functions such as resource servers, authorization servers, and dynamic client registration.

This is an MCP server designed for Atomic CRM that allows AI assistants to securely read and write data from CRM instances through secure OAuth 2.1 authentication and SQL query tools, and automatically enforces row-level security policies.

MCP Plexus is a Python framework based on FastMCP 2.7 for building secure and scalable multi-tenant MCP servers. It supports OAuth 2.1 integration and API key management, providing an isolated environment and tool access control for modern AI applications.

An enterprise-level SQLite MCP server that provides OAuth 2.1 authentication and 89 dedicated tools, supports dual backends (WASM/Native), transaction processing, window functions, and advanced data analysis features.

The LibSQL Model Context Protocol Server is a service application built on Deno 2.1, used to connect to LibSQL databases, provide schema information, and support table queries. It handles requests such as resource listing, schema reading, prompt completion, and SQL queries through the Model Context Protocol (MCP), supporting both authenticated and unauthenticated database access, balancing flexibility and security.

MyTaskly MCP Server is a middleware based on the Model Context Protocol, providing an API gateway with OAuth 2.1 JWT authentication for the MyTaskly task - management application. It includes 20 tools and can format the data from the FastAPI backend into a response friendly to React Native mobile devices.