Mostly Harmless

Mitchell Hashimoto tweeted this week: <blockquote class="twitter-tweet" data-dnt="true" data-conversation="none"><p lang="en" dir="ltr">Beware people obsessed with outcomes instead of building <em>outcome machines</em>.

import { Image } from 'astro:assets'; import heroLoopToGraph from '.

import { Image } from 'astro:assets'; import teamDirectoryImg from '.

import Callout from "@components/blog/Callout.astro"; import generativeUiVideo from '.

One year ago, I reorganized Prefect to operate as a sustainable, customer-funded business.

import Callout from "@components/blog/Callout.astro"; MCP servers scale in a way that punishes success.

FastMCP 3.0 is stable and generally available. pip install fastmcp -U It's been about a month since the first beta.

import Callout from "@components/blog/Callout.astro"; The FastMCP 3 beta has been running for a few weeks now, and we've been busy.

import Callout from "@components/blog/Callout.astro"; <Callout color="blue"> tl;dr Colin is an experimental context engine that can load dynamic information into agent skills and keep them fresh.

import Callout from "@components/blog/Callout.astro"; FastMCP 3.0 is our largest release ever.

import Callout from "@components/blog/Callout.astro"; I have a confession to make.

I think SEP-1577 is the sleeper hit of the new Model Context Protocol (MCP) specification.

Most MCP usage is invisible.

Every company will have a context layer.

import Callout from "@components/blog/Callout.astro"; import { Image } from 'astro:assets'; import downloads_img from '.

import Callout from "@components/blog/Callout.astro"; One of the hardest parts of maintaining an open-source project is saying "no" to a good idea.

import Callout from "@components/blog/Callout.astro"; We're excited to announce the release of FastMCP 2.12, a major update that reflects a pivotal moment for the MCP ecosystem.

import Callout from "@components/blog/Callout.astro"; FastMCP has quickly become the most popular framework for building MCP servers, and its momentum has been incredible to watch.

import Callout from "@components/blog/Callout.astro"; Here's a dirty secret about MCP servers: almost nobody implements authentication.

import { Image } from 'astro:assets'; import badFeeling from '.

import Callout from "@components/blog/Callout.astro"; This morning we released FastMCP 2.9, which includes a new, MCP-native approach to middleware.

A common question I hear when teams start building for AI is, "Why can't agents just use our REST API instead of MCP?"

import Callout from "@components/blog/Callout.astro"; As the author of FastMCP, it might seem strange that I haven’t prioritized an MCP server for Prefect.

import Callout from "@components/blog/Callout.astro"; What do you do when the perfect tool... isn't so perfect?

import Callout from "@components/blog/Callout.astro"; FastMCP's journey continues at a thrilling pace.

import Callout from "@components/blog/Callout.astro"; If you're working with the Model Context Protocol (MCP), you're on the front lines of AI innovation.

import { Image } from 'astro:assets'; import history_img from '.

import Callout from "@components/blog/Callout.astro"; FastMCP 2.3 was just released, including the most-requested feature by a mile: Streamable HTTP for both FastMCP servers and clients.

Previously in FastMCP, the powerful Context object – the gateway to MCP features like logging, progress reporting, resource access, and client LLM sampling – was only easily accessible in MCP tool functions.

In the FastMCP 2.0 release post, I highlighted how the project's focus has evolved from simply creating MCP servers in 1.0, to making it easier to work with the growing ecosystem in 2.0.

I'm thrilled to announce the release of FastMCP 2.0!

This week I made a decision to ensure Prefect's long-term success by reorganizing our company to operate as a profitable, customer-funded business.

import { Image } from "astro:assets"; import bridge from ".

Last week, Anthropic introduced the Model Context Protocol (MCP), a new standard for connecting AI models to data and tools.

I'm a big fan of Bluesky, and I just added comments to this blog by leveraging its open protocol.

import { Image } from 'astro:assets'; import slackScreenshot from '.

When o1 was released, I wrote that internal reasoning - even iterative reasoning - didn't represent agentic behavior.

import Callout from "@components/blog/Callout.astro"; import { Image } from 'astro:assets'; import coinToss from '.

Covid caused many statistical anomalies, but my favorite is the spike in searches for "thank you."

Recently, I added hovering tooltips to the list of blog posts, but I really didn't like how they flashed for a moment when you tapped a link on mobile.

I'm really excited about the release of ControlFlow v0.10, which introduces a significant new feature: a flexible and practical memory system for AI agents.

import { Image } from 'astro:assets'; import banner from '.

I know you've heard it: "Why can't ChatGPT do this?"

We're drowning in AI-generated words, a trend that will only accelerate as the technology improves and becomes more accessible.

OpenAI's o1's reasoning ability is essentially chain-of-thought behind the API, which makes it a much more powerful model for handling nuanced problems.

<div class="flex justify-center"> <iframe width="560" height="315" src="https://www.youtube.com/embed/ZS90l4L2t6k?