Hundreds of servers are impacted by the "NeighborJack" vulnerability that allows access to anyone within the same local network.
More than 7,000 Model Context Protocol servers, which enable artificial intelligence app access to data outside their training models, around the world are exposed to the internet.
Of over 15,000 servers, hundreds of which are impacted by the "NeighborJack" vulnerability that allows access to anyone within the same local network, a report from Backslash Security showed.
Nearly 70 of the MCP servers also had unnecessary permissions, uncontrolled input handling, and other significant vulnerabilities. Attackers could leverage such issues not only to facilitate total host machine hijacking, but also context poisoning intrusions that involve large language model data tampering, according to researchers, who emphasised that none of the examined MCPs have been malicious.
Organisations have been advised to mitigate potential exploitation of MCP servers by restricting local network interface access, limiting file system access, conducting external input validation, adopting robust authentication and access controls, and preventing internal log exposure in AI responses.
Written by
Dan Raywood is a B2B journalist with 25 years of experience, including covering cybersecurity for the past 17 years. He has extensively covered topics from Advanced Persistent Threats and nation-state hackers to major data breaches and regulatory changes.
He has spoken at events including 44CON, Infosecurity Europe, RANT Forum, BSides Scotland, Steelcon and the National Cyber Security Show, and served as editor of SC Media UK, Infosecurity Magazine and IT Security Guru. He was also an analyst with 451 Research and a product marketing lead at Tenable.
