The last time I dived into building a toy MCP service for a school library assistant, which helps you search for books, borrow copies, and return them. I quickly realized this wasn’t practical. Without authentication and authorization, the service was only useful for an administrator with full access.

What if we want to expose a real service? Security needs to be a first-class citizen.

MCP service itself is not that mysterious. It’s essentially built upon HTTP protocol with an extra layer of protocol and formatting. We can leverage all the concept for building security for HTTP services, like TLS, OAuth, etc. With the FastMCP framework we can extend the Authn/Authz, just like the Python backend development process.

This is a toy implementation, but I think can demo the basic ideas for MCP service and LLM integration.

Code here: https://github.com/hxy9243/agents/tree/main/librarian

See last blog: https://blog.kevinhu.me/2025/08/09/Building-MCP-with-DSPy/

Read More

Recently I’ve been looking into MCP and how it integrates with development framework. I tried with some hands-on tinkering, and learned quite a bit. Here’s my learning and some reflections.

Code here: https://github.com/hxy9243/agents/tree/main/librarian

What’s MCP

Bird’s Eye View

MCP (Model Context Protocol) is a standard way for AI agents to securely connect to your services. It provides a uniform interface for tools, resources, and prompts, enabling seamless integration between AI systems and external services.

Clients like VSCode, Gemini Code, or Claude Code can now integrate with different tools and services and become incredibly powerful, from reading PDFs, search for websites, read your Google Drive files, or book plane tickets for you. You could implement the MCP service once and easily install in all kinds of the AI assistants of your choice.

With this standardization, you can implement your MCP server and they can directly integrate with your user’s agents, assistants, or more complicated workflows. They can call and leverage your tools with a standardized interface.

Think of an AppStore moment for app discovery and AI integration.

Read More

Page table is where Linux stores virtual to physical page address translation, and its size can get huge when memory usage is high. One way to reduce the size of page tables, and reduce the number of page faults, is to use huge pages. I’ve been digging some information on hugepages for my own curiosity, and it looks like Linux has pretty good support for huge pages. And this blog serves as a quick note on my readings.

Read More

Recently my colleague and I were working to port V8 JS engine as one of our benchmarks. We used it as it’s a widely-used library on devices we cared about, and we believed it’s a well-maintained, high code quality project. Or at least we thought.

Read More