Harden Your MCP Server NOW Before Anthropic Forces You To

A researcher at adversa.ai just demonstrated a zero-click RCE chain that starts with a calendar invite and ends with full code execution on your machine. The attack path goes through MCP tool chaining - low-risk tools escalating to high-risk local executors. Anthropic was notified about a related flaw in Claude Extensions (DXT). They declined to fix it. That's not a hypothetical. Cyberwarzone reported active exploitation artifacts today, March 11th, 2026. If you're running an MCP server in production, you need to harden it right now. Not next sprint. Now. The Attack Chain Here's what adversa.ai documented: Attacker sends a calendar invite with crafted metadata Agent's calendar tool processes the invite (low-risk, read-only tool) The metadata contains instructions that the agent interprets as actionable Agent chains from calendar tool to a file system tool or code executor Arbitrary code runs on the host machine The critical insight: each individual tool permission seems reasonable. A c