pamela fox's blog

When we build agents, we often want to give them the ability to browse the web: open webpages, navigate from one page to the other, and read the content of a webpage.

Model Context Protocol (MCP) is an open protocol that describes how agents can connect to external tools and data sources, and is now widely supported by the most popular coding agents (like GitHub Copilot, Claude Code, and Codex) and agent frameworks (li…

I'm writing this post on the flight back from PyCon US 2026 in Long Beach, California.

The Model Context Protocol (MCP) gives AI agents a standard way to call external tools, but things get more complicated when those tools need to know who the user is.

MCP servers contain tools, and each tool is described by its name, description, input parameters, and return type.

When I was a kid, one of my first Java applets was a UI for choosing outfits by mixing and matching different articles of clothing.

I recently spoke at the PyAI conference, put on by the good folks at Prefect and Pydantic, and I learnt so much from the talks I attended.

In December, we presented a series about MCP, culminating in a session about adding authentication to MCP servers.

MCP is one of the fastest growing technologies in the Generative AI space this year, and the first AI related standard that the industry has really embraced wholeheartedly.

My colleague and I just wrapped up a live series on Python + AI, a nine-part journey diving deep into how to use generative AI models from Python.

What I like about MCP servers: they give me lots of great tools that can make my agents more powerful, with very little work on my side. 🎉 What I don't like about MCP servers: they give me TOO many tools!

I do not consider myself an expert in generative AI, but I now know enough to build full-stack web applications on top of generative AI models, evaluate the quality of those applications, and decide whether new models or frameworks will be useful.

OpenAI released the GPT-5 model family today, with an emphasis on accurate tool calling and reduced hallucinations.

When we develop user-facing applications that are powered by LLMs, we're taking on a big risk that the LLM may produce output that is unsafe in some way - like responses that encourage violence, hate speech, or self-harm.

I have a problem: I'm addicted to making new repositories on GitHub.

When we're building automation tools in 2025, I see two main approaches: Agent + MCP: Point an LLM-powered Agent at MCP servers, give the Agent a detailed description of the task, and let the Agent decide which tools to use to complete the task.

In the summer of 2006, I discovered the blossoming world of web APIs: HTTP APIs like the Flickr API, JavaScript APIs like Google Maps API, and platform APIs like the iGoogle gadgets API.

Back in 2014, I had a brush with cervical cancer.

There are many ways to learn Python online, but there are also many people out there that want to learn Python for multiple reasons - so hey, why not add one more free Python course into the mix?

Whenever I am teaching Python workshops, tutorials, or classes, I love to use GitHub Codespaces.

For Pycon 2025, I created a poster exploring vector embedding models, which you can download at full-size.

If you are using the DefaultAzureCredential class from the Azure Identity SDK while your user account is associated with multiple tenants, you may find yourself frequently running into API authentication errors (such as HTTP 401/Unauthorized).

I ❤️ when companies offer free tiers for developer services, since it gives everyone a way to learn new technologies without breaking the bank.

Update: The approach has slightly changed (in a good way!).

The azure-search-openai-demo repository was first created in March 2023 and is now the most popular RAG sample solution for Azure.