A third of 36 popular MCP servers fail agents on usability
I graded 36 popular MCP servers on agent usability. A third got a D or F
Teng Li linted 36 popular MCP servers with his tool mcpgrade: 11 scored D or F. The main culprit is undocumented parameters—firecrawl had 132 out of 134 errors from bare params, and MongoDB and Notion official servers are similarly bare. In live model evals, poorly documented servers dropped tool-selection accuracy from 100% to 84%, and refusal rate on out-of-scope tasks fell from 100% to 50%. The fix is simple: add .describe() to every parameter. context7 already did it and jumped from C to a perfect score.
Why it matters: The author graded 36 popular MCP servers with a self-written tool, and 11 got a D or F, mostly for undocumented parameters.