Reproduce “A Large-Scale Evolvable Dataset for Model Context Protocol Ecosystem and Security Analysis” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Zhiwei Lin, Bonan Ruan, Jiahao Liu, Weibo Zhao

Researchers at the National University of Singapore curated MCPCorpus, a large-scale dataset containing approximately 14,000 Model Context Protocol (MCP) artifacts, to enable comprehensive analysis of the MCP ecosystem. Initial analysis of the dataset revealed a highly skewed distribution of project popularity and the dominance of Python, TypeScript, and JavaScript as primary implementation languages.

Key insights

  • MCPCorpus provides a structured, comprehensive, and evolving view of the Model Context Protocol (MCP) ecosystem.
  • The dataset enables systematic, large-scale analysis of adoption trends, implementation diversity, security postures, and overall ecosystem health.
  • The work transitions the field from anecdotal observations and limited analyses to data-driven insights for tool-augmented LLM integration.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.