{"slug": "rethinking-mcp-security-a-large-scale-study-of-runtime-mcp-servers", "title": "Rethinking MCP Security: A Large-Scale Study of Runtime MCP Servers", "summary": "Researchers at an undisclosed institution created MCPZoo, the largest collection of 64,611 Model Context Protocol (MCP) servers for dynamic analysis, and found that existing security scanners are unreliable, with less than 50% of alerts being true positives and significant inconsistency across scanners, despite reporting 96.89% of servers as risky. The study highlights the need for more accurate security assessments as MCP servers become critical for LLM-based agents.", "body_md": "# Computer Science > Cryptography and Security\n\n[Submitted on 13 Jul 2026]\n\n# Title:Rethinking MCP Security: A Large-Scale Study of Runtime MCP Servers and Security Scanner Reliability\n\n[View PDF](/pdf/2607.11086)\n\n[HTML (experimental)](https://arxiv.org/html/2607.11086v1)\n\nAbstract:The Model Context Protocol (MCP) has rapidly established itself as a standard interface for enabling LLM-based agents to interact with external tools and services. As MCP servers are increasingly entrusted with security-sensitive operations, understanding their real-world risks has become critical. In practice, due to the absence of large-scale runtime MCP servers, such understanding largely relies on security scanners applied to a small number of cases, yet the reliability of these assessments remains unclear.\n\nIn this study, we revisit how MCP security is measured. We present MCPZoo, the largest collection of MCP servers for dynamic analysis to date. MCPZoo is constructed through a multi-agent framework for transforming in-the-wild static repositories into dynamic services. The framework emulates how human experts build, diagnose, and iteratively repair deployment and runtime defects by combining environment inference with feedback-driven refinement. To ensure practical interactivity at runtime, the servers are validated via real protocol interactions. As a result, MCPZoo contains 64,611 unique MCP servers (113,927 in total), with more than 37,288 supporting dynamic analysis. Leveraging MCPZoo, we conduct the first ecosystem-scale measurement of MCP servers and the scanners that analyze them. While existing scanners report that 96.89% of servers are risky, we find that these signals are unreliable. In particular, manual validation shows that less than 50% of sampled alerts are true positives, and scanner outputs exhibit clear inconsistency across scanners. Overall, MCPZoo enables large-scale, reproducible measurement of MCP server security and exposes limitations of current scanning practices. We further release a public query interface to support practical risk assessment of MCP servers.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/rethinking-mcp-security-a-large-scale-study-of-runtime-mcp-servers", "canonical_source": "https://arxiv.org/abs/2607.11086", "published_at": "2026-07-14 09:41:43+00:00", "updated_at": "2026-07-14 10:18:53.321151+00:00", "lang": "en", "topics": ["ai-safety", "ai-agents", "large-language-models", "ai-infrastructure", "ai-research"], "entities": ["MCPZoo", "Model Context Protocol"], "alternates": {"html": "https://wpnews.pro/news/rethinking-mcp-security-a-large-scale-study-of-runtime-mcp-servers", "markdown": "https://wpnews.pro/news/rethinking-mcp-security-a-large-scale-study-of-runtime-mcp-servers.md", "text": "https://wpnews.pro/news/rethinking-mcp-security-a-large-scale-study-of-runtime-mcp-servers.txt", "jsonld": "https://wpnews.pro/news/rethinking-mcp-security-a-large-scale-study-of-runtime-mcp-servers.jsonld"}}