aiqbench analysis
This study provides the first comprehensive security audit of internet-facing Model Context Protocol (MCP) servers, revealing critical gaps such as widespread lack of OAuth authentication and uncontrolled shell execution capabilities. By combining passive discovery with active testing via a new open-source framework, researchers identified 68 distinct vulnerabilities including SQL injection and prompt template attacks across hundreds of production instances. The findings highlight the urgent need for standardized security reviews in rapidly deployed AI infrastructure before they are exposed to public networks.
Exposed by Design: A Dynamic Security Assessment of Internet-Facing MCP Servers at Scale
arXiv:2608.00150v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has seen rapid adoption since its November 2024 launch, with over 21,000 server instances detectable on the public internet. We present the first dynamic behavioral security assessment of internet-facing MCP servers, combining passive discovery across eleven data sources (crt.sh, HuggingFace, GitHub, npm, Smithery, PyPI, Censys, FOFA, Shodan, glama.ai, and pulsemcp.com) with active dynamic testing using Corvus, a purpose-built framework implementing 34 test modules covering 10 MCP-specific vulnerability classes. Across four measurement runs spanning July 2026, we confirm 640 production MCP servers and dynamically audit 414, uncovering 68 reportable vulnerabilities including SQL injection, SSRF targeting cloud metadata services, prompt template injection, and path traversal via cursor manipulation. We find that 91.8% of dynamically audited servers lack OAuth authentication, 687 tool instances across confirmed servers expose shell execution capabilities without access controls, and 41.6% of confirmed servers disappear within three days between consecutive measurement runs---indicating rapid deployment cycles without security review. We report on our responsible disclosure pipeline and release Corvus as an open-source framework for MCP security evaluation.
Abstract:The Model Context Protocol (MCP) has seen rapid adoption since its November 2024 launch, with over 21,000 server instances detectable on the public internet. We present the first dynamic behavioral security assessment of internet-facing MCP servers, combining passive discovery across eleven data sources (this http URL, HuggingFace, GitHub, npm, Smithery, PyPI, Censys, FOFA, Shodan, this http URL, and this http URL) with active dynamic testing using Corvus, a purpose-built framework implementing 34 test modules covering 10 MCP-specific vulnerability classes. Across four measurement runs spanning July 2026, we confirm 640 production MCP servers and dynamically audit 414, uncovering 68 reportable vulnerabilities including SQL injection, SSRF targeting cloud metadata services, prompt template injection, and path traversal via cursor manipulation. We find that 91.8% of dynamically audited servers lack OAuth authentication, 687 tool instances across confirmed servers expose shell execution capabilities without access controls, and 41.6% of confirmed servers disappear within three days between consecutive measurement runs---indicating rapid deployment cycles without security review. We report on our responsible disclosure pipeline and release Corvus as an open-source framework for MCP security evaluation.
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
arXiv:2608.00150 [cs.CR]
(or arXiv:2608.00150v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2608.00150 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both 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.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 274 words
Related coverage

[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026
October 2026 Patch Tuesday: 1,413 CVEs Include Three Zero-Days and 75 Critical Vulnerabilities
CrowdStrike Blog · Oct 13, 2026

[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · Sep 17, 2026
.webp%3Fssl%3D1&w=320)
Top 50 Best Penetration Testing Companies in 2026
Cybersecurity News · Jul 31, 2026