Decision and Context Systems for AI
At lyr3 I write about building practical intelligence into organizations — where strategy meets AI, and insight replaces noise. In my work with CEOs and leadership teams, I explore how small, well-designed systems can make organizations sharper, decisions clearer, and technology more understandable and genuinely effective.
Credible strategic support and blind-spot detection remain serious challenges for the current generation of AI systems. AI models, trained for helpfulness and likeability, often drift toward what can only be described as “performative agreeableness.” It’s why people push them to “get real with me”—they sense the flattening of truth beneath the friendliness.
A manifest is the configuration file that tells clients like Claude what an MCP server can do. It declares the tools, resources, and prompts the server offers, plus some basic metadata like its name, version, and description. In short, it’s how an MCP server introduces itself and explains how to talk to it.
Until now, you wouldn’t have seen one because clients had to actually connect to a server before discovering its capabilities. That’s changing with the November 2025 spec update, which introduces .well-known URL discovery. This is a big deal. It means MCP servers will be able to publish their manifest in a predictable public location—like how websites use sitemap.xml—so tools, registries, and even search engines for MCP can index what’s out there without needing a live connection.
That shift makes the manifest more than just internal config. It becomes the public face of an MCP server—the thing that lets the ecosystem browse, catalog, and connect everything together.
If you’ve never heard of manifests before, that’s normal. They’ve been working quietly in the background. But the new .well-known requirement is about to make them front and center in how AI systems discover and connect across the MCP network.
This article is published on MCPalign.
This article is published on MCPalign.
This article is published on MCPalign.
The Model Context Protocol (MCP) ecosystem has exploded. In just months, developers have published hundreds of servers and thousands of tools. It’s a remarkable show of creativity: everything from lightweight utilities that return the time of day to heavyweight servers that can administer databases, manage cloud infrastructure, or even control a computer.
We analyzed 1,945 tools across 238 servers in the MCP Registry to understand how tools are distributed.
This week, we’re launching a new phase of research at Lyr3: digging into the tools that power the MCP ecosystem.
So far:
We’ve collected data on > 420 MCP servers.
Across ~300 of them, we’ve identified 1,400+ distinct tools, tool descriptions and inputs.
