Menu

Your AI Coding Agent Is Installing Abandoned MCP Servers From Its Training Data
📰

Your AI Coding Agent Is Installing Abandoned MCP Servers From Its Training Data

DEV Community: appsec·Cor E·1 day ago
#mM3KjNQo
#devtoappsec#devto#dev#package#agent
Reading 0:00
15s threshold

Glow Labs published research on what they're calling MCPhantom, and the uncomfortable part is that nobody attacked anyone.

Their finding: AI coding agents (Claude Code, Cursor, Codex CLI, and others, across Anthropic, OpenAI, and xAI models) routinely install deprecated, archived Anthropic MCP reference servers. Not because a user asked for them. Because those package names are all over the models' training data, so that's what the model reaches for when it needs an MCP server. The current official servers lose to the stale ones the model remembers.

Those archived packages carry four high-severity vulnerabilities, including a Puppeteer server RCE that's exploitable via prompt injection. They've racked up 17M+ npm downloads since July 2025. No malicious actor is involved. Glow says no exploitation has been observed so far.

I'd call that the whole point. There's no attacker to catch.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.