lyr3: AI, PE and Change

Sep 30, 2025

How We Test

LLMs don’t just need to answer questions—they need to choose the right tools when connected to an MCP server. Our testing system is designed to measure exactly that, giving us a clear picture of how well models navigate real-world tool use.

Sep 26, 2025

Case Study: How Manifest Alignment Boosted Tool Use Performance from 70% to 83% for Cooking MCP

Large language models don’t just rely on their training—they also depend on how tools are described and exposed through manifests. Even small wording choices in a manifest can make the difference between a model using the right tool confidently or skipping it altogether.

Sep 25, 2025

Case Study: How a Single Manifest Change Boosted LLM Accuracy from 33% to 83% in a Key Use Category

## The Challenge We were testing a simple MCP todo server with three tools: createTodo, listTodos, and a completion tool. The original completion tool was named completeTodo with the bare description: “Mark a todo item as completed.”

Sep 25, 2025

Deterministic vs. Interpretive MCP Servers: Speaking the Same Language

MCP isn’t just about exposing tools. It’s about creating an efficient and effective understanding of a server in the eye of the ClientAI. This communication is guided by the manifest and, by extension, the initialization and tool calls. For simplicity, we’ll use “manifest” to represent that entire package. In effect, the manifest becomes the dictionary of the language between server and AI.

Sep 24, 2025

Potential and Pitfalls: Security Lessons from Real-World MCP Tools

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.

Sep 18, 2025

MCP Tool Distribution

We analyzed 1,945 tools across 238 servers in the MCP Registry to understand how tools are distributed.

Sep 17, 2025

MCP Tool Research

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.

Sep 12, 2025

Link: You are Doing MCP Wrong

Good read of what MCP is and is not from Jim Clark at Docker. link.

Sep 11, 2025

MCP Registry

Lyr3.com is happy to present its MCP Registry as a beta.

Sep 9, 2025

NEWS: MCP Continues Reach Growth - Sept 9

MCP continues to expand its reach across enterprise and developer ecosystems, with new use cases, platform adoption, and benchmarks revealing both promise and challenges.

Let’s figure out what AI
actually looks like for you

No pitch deck. A conversation about your portfolio, your thesis, and whether I can move the numbers.

Work with me