What a Random Draw from the MCP Registry Contains, and What Tool-Use Benchmarks Contain Instead
Studies of the Model Context Protocol (MCP) server ecosystem draw their samples in ways that quietly select for servers that work: reference sets, popularity lists, hand-curated frames, or pipelines that repair a server until it starts. We report what an unrepaired probability sample actually contains. From a 24,135-se...
H. M. Afsar
· 0 citations