Practical notes, talks, projects, and hands-on guides for using MCP to connect AI applications to tools and data, build servers and apps, and secure access with OAuth, fine-grained authorization, and policies for individual tool calls.
A hands-on course on securing Model Context Protocol (MCP) servers and MCP apps with Pomerium, covering OAuth 2.1, upstream OAuth to APIs like GitHub, and per-user, per-tool authorization from dev to production.
A production-ready TypeScript starter for building, testing, and shipping MCP servers.
A remote MCP server for browsing dev.to articles, users, and comments from an MCP-compatible client.
A well-architected starter for building MCP Apps with TypeScript, React widgets, the OpenAI Apps SDK, and Pomerium.
A multi-server MCP chat client demonstrating authenticated remote access and Zero Trust authorization.
