I graded 36 popular MCP servers on agent usability. A third got a D or F
A developer analyzed 36 popular Model Context Protocol (MCP) servers and found that many fail to provide usable tools for AI agents despite being spec-compliant. The study highlights that poor naming, descriptions, and schema design often hinder agent performance.
Why it matters
As AI agents become more prevalent, the quality and usability of integration protocols are critical for ensuring reliable automation and tool usage.
Your MCP server can be 100% spec-compliant and still be unusable by an agent.
The Model Context Protocol spec tells you how to transport tools: JSON-RPC framing, capability negotiation, schema shapes. It says nothing about whether a model can actually use what you serve — whether it picks the right tool out of your catalog, fills the arguments correctly, or burns 8k tokens parsing your schemas on every single request.
I integrate first- and third-party MCP connectors into a production AI agent for a living, and I kept seeing the same failure: servers that pass every compliance check, yet the model calls the wrong tool, hallucinates arguments, or ignores the tool entirely. The problems were never in the protocol layer. They were in the parts no one lints: descriptions, naming, schema design.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in