Registry Descriptions Go Stale Unevenly: An 89-Day Measurement of Model Context Protocol Drift, and Why Drift-Ranked Re-Auditing Under-Covers It
Gautam Bharti
Abstract
Security studies of the Model Context Protocol (MCP) ecosystem share a design: each audits a registry at a single point in time. None reports how long the registry descriptions those audits judged stay current - a necessary condition for any description-level finding to still apply, though not a sufficient one: we measure the shelf-life of the audited text, not the validity of a security finding itself (Sec. 7.1). We reconstruct 120 observations of the official MCP registry over 88.6 days, covering 19,099 distinct servers as it grew from 3,510 to 18,966. Our central result is a policy one: you cannot keep description-level findings current by re-auditing the servers that drift most. At a top-5% re-audit budget, ranking by prior drift catches only ~20% of the previously-seen servers whose description changes in a held-out window - versus ~27% for descriptor drift overall - and only ~10% of all description changers. The limit is not unpredictability: the ranking still buys ~4x lift. It is that the description surface is sparse - 8.6% of servers ever rewrite one, against 24.8% for descriptors - and that roughly half of all description changes land on new arrivals a history ranking cannot reach, so the same lift buys far less coverage. The control that fits is content-binding - revalidate the moment a description's hash moves - plus a sized periodic full-catalog sweep; a drift-history ranking is at best a partial, blind-to-new-arrivals control. This is scanner hygiene for a description-level auditor, not a runtime trust signal. Of servers observed across at least ten intervals, three-quarters never change, the most active 5% generate 61% of all change events, and only 11.9% of a cohort's descriptors change within 30 days; naive compounding predicts 35.8% at 30 days (73% at 89), a heavy-tail overestimate we use only as a diagnostic. We release the panel, figure generator, and analysis code.
Create a lesson
Related papers
ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks
Jeonghye Kim, Minseon Kim, Young Jin Kim et al.
Evaluating the Health of Open-Source Smart City Platforms
Rodrigo Bravo Simões, Fernando Brito e Abreu, Vasco Amaral
From Component Snapshots to Lifecycle Traces: Agent-Based Software Composition Analysis
Chaofan Li, Zhengduo Xue, Chengxiang Li et al.
A Study on the Impact of Natural Language Differences in Prompts on Automatic Code Generation Using LLMs
Haruka Tokumasu, Masanari Kondo, Alexander Serebrenik et al.
A Study of the Reliability of Agentic AI-Generated Programs
Ayesha Shafique, Barton P. MIller, Elisa R. Heymann
Relationally Guided Use Case Modeling with LLMs
Guangyu Wang, Bangqi Li, Ji Wu et al.