Security researchers have issued a warning after discovering the first malicious Model Context Protocol (MCP) server in the wild.
MCP servers are widely used to allow AI agents to handle emails and run database queries, which means giving them access to all email traffic, according to Koi Security.
Postmark MCP Server is downloaded 1,500 times per week, and has been integrated into hundreds of developer workflows.
However, since version 1.0.16 was released, Koi said it's been copying every single email - including invoices, internal memos, and confidential documents - to the developer's personal server.
"These MCP servers run with the same privileges as the AI assistants themselves - full email access, database connections, API permissions - yet they don't appear in any asset inventory, skip vendor risk assessments, and bypass every security control from DLP to email gateways," said Koi co-founder Idan Dardikman.
"By the time someone realizes their AI assistant has been quietly BCCing emails to an external server for months, the damage is already catastrophic."
There is a completely legitimate GitHub repo with the same name, officially maintained by Postmark, researchers noted. However, the attacker took the legitimate code from the repo, added his malicious BCC line, and published it to npm under the same name.
"This is the world’s first sighting of a real world malicious MCP server. The attack surface for endpoint supply chain attacks is slowly becoming the enterprise’s biggest attack surface," warned Dardikman.
"We're talking about 3,000 to 15,000 emails every day flowing straight to giftshop.club. And the truly messed up part? The developer didn't hack anything. Didn't exploit a zero-day. Didn't use some sophisticated attack vector,” he added/
“We literally handed him the keys, said 'here, run this code with full permissions', and let our AI assistants use it hundreds of times a day."
Malicious MCP server scrapped, but users still at risk
When Koi contacted the developer, Dardikman said he immediately deleted the package from npm. However, any organizations already using it will continue to be affected.
Users of version 1.0.16 should remove it immediately and rotate any credentials that may have been exposed, the company warned. They should also audit every MCP server they're using, making sure it's an official repository, reviewing the source code, and checking for changes in every update.
Koi said it reported the issue to npm, adding that the discovery raises broader concerns over MCP security.
"The postmark-mcp backdoor isn't just about one malicious developer or 1,500 weekly compromised installations. It's a warning shot about the MCP ecosystem itself," he said.
"We're handing god-mode permissions to tools built by people we don't know, can't verify, and have no reason to trust. These aren't just npm packages - they're direct pipelines into our most sensitive operations, automated by AI assistants that will use them thousands of times without question."
Make sure to follow ITPro on Google News to keep tabs on all our latest news, analysis, and reviews.
MORE FROM ITPRO
-
September rundown: The UK becomes an AI playgroundITPro Podcast Big tech has announced tens of billions in infrastructure investments for the UK – how will it help?
-
Microsoft’s new ‘marketplace’ lets customers pick and choose cloud, AI solutionsNews The Microsoft Marketplace looks to streamline customer access to AI and cloud services
-
NCA confirms arrest after airport cyber disruptionNews Disruption is easing across Europe following the ransomware incident
-
Cyber skills shortages are pushing firms into dangerous shortcuts – and it’s putting them at huge risk of security breachesNews Chronic cyber skills shortages mean many businesses are implementing quick fixes
-
Pentesters are now a CISOs best friend as critical vulnerabilities skyrocketNews Attack surfaces are expanding rapidly, but pentesters are here to save the day
-
Hackers are disguising malware as ChatGPT, Microsoft Office, and Google Drive to dupe workersNews Beware of downloading applications like ChatGPT, Microsoft Office applications, and Google Drive through search engines
-
Generative AI attacks are accelerating at an alarming rateNews Two new reports from Gartner highlight the new AI-related pressures companies face, and the tools they are using to counter them
-
A terrifying Microsoft flaw could’ve allowed hackers to compromise ‘every Entra ID tenant in the world’News The Entra ID vulnerability could have allowed full access to virtually all Azure customer accounts
-
‘Channel their curiosity into something meaningful’: Cyber expert warns an uptick of youth hackers should be a ‘wake-up call’ after teens charged over TfL attackNews Encouraging youths to engage in positive tech initiatives will guide them down the right path and away from nefarious activities
-
Microsoft and Cloudflare just took down a major phishing operationNews RaccoonO365’s phishing as a service platform has risen to prominence via Telegram
