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
-
Google wants to take hackers to courtNews You don't have a package waiting for you, it's a scam – and Google is fighting back
-
How cyber leaders can communicate with the boardIn-depth With the cost of cyber attacks clearer than ever before, how can CISOs use this data to convince boards that cybersecurity is worth the investment?
-
Google wants to take hackers to court
News You don't have a package waiting for you, it's a scam – and Google is fighting back
-
Laid off Intel engineer accused of stealing 18,000 files on the way outNews Intel wants the files back, so it's filed a lawsuit claiming $250,000 in damages
-
GitHub is awash with leaked AI company secrets – API keys, tokens, and credentials were all found out in the openNews Wiz research suggests AI leaders need to clean up their act when it comes to secrets leaking
-
When cyber professionals go rogue: A former ‘ransomware negotiator’ has been charged amid claims they attacked and extorted businessesNews The attackers are alleged to have demanded ransoms of up to $10 million
-
CISA just published crucial new guidance on keeping Microsoft Exchange servers secureNews With a spate of attacks against Microsoft Exchange in recent years, CISA and the NSA have published crucial new guidance for organizations to shore up defenses.
-
US telco confirms hackers breached systems in stealthy state-backed cyber campaign – and remained undetected for nearly a yearNews The hackers remained undetected in the Ribbon Communications’ systems for months
-
Google says reports of a 'huge' Gmail breach affecting millions of users are false, againNews Reports of a major Gmail affecting millions of users have been flooding the web this week – Google says they're "false" and you've nothing to worry about.
-
Enterprises can’t keep a lid on surging cyber incident costsNews With increasing threats and continuing skills shortages, AI tools are becoming a necessity for some
