SOURCE-LINKED INTELLIGENCE

What a Random Draw from the MCP Registry Contains, and What Tool-Use Benchmarks Contain Instead

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

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-server registry census we draw 400 npm/stdio servers with a published seed and probe each one over the wire. Only 48.8% complete an initialize handshake, against 66.7% for a hand-curated frame measured with the same instrument, and the dominant failure is not missing credentials (1

Read original source ↗ Open in workspace

recordType

paper

region

Global