Skip to main content
Mallory
← Back to News
ai-platform-securitythreat-infrastructure-trackingunmanaged-asset-discoverydata-exfiltration-method

MCPJacking Exposes 155 Stale MCP Registry Entries to Domain Takeovers

Emerging Technology Risk · 3 sources · Updated 3mo ago · First seen Sep 3, 2026

MCPJacking Exposes 155 Stale MCP Registry Entries to Domain Takeovers

AIR Security researchers identified 155 Model Context Protocol (MCP) servers in the Official MCP Registry whose underlying services were offline while their associated domains had expired. An attacker can re-register one of those domains and operate a malicious server at the trusted registry address, potentially causing AI agents that retain the stale MCP configuration to connect to attacker-controlled infrastructure.

A hijacked MCP server could alter tool definitions, inject prompts, redirect agent actions, and exfiltrate data available to the agent. The exposure highlights unresolved MCP supply-chain weaknesses, including insufficient runtime endpoint verification, unsigned or unpinned server dependencies, and permissive tool execution; organizations should inventory MCP integrations, remove stale entries, verify and pin server identities, enforce least privilege and approval controls, and govern access through allowlists, internal registries, and monitoring.

New surface, new adversariesTrack how attackers are adapting to this technology.
Track this risk
Event timeline

How this story unfolded

Events from the most recent confirmed update back to the earliest known activity.

5 events · Aug 27, 2026
  1. Aug 27, 20263mo ago

    AIR Security publishes MCPJacking research

    AIR Security researchers Nadav Dadush, Eliad Mualem, and Roi Snir described MCPJacking, a supply-chain attack in which expired domains behind stale official MCP Registry entries can be re-registered and used to serve attacker-controlled MCP servers. Their scan identified 155 registry entries still marked trusted despite nonfunctioning underlying services and expired domains.

    MCPJacking : 155 serveurs MCP détournés via des domaines expirés dans le registre officiel | CyberVeille
  2. Reported Apr 17, 20252y ago

    Wiz demonstrates RCE through an external MCP server

    Wiz researcher Gal Nagli published a proof of concept showing that an external MCP server intended to parse GitHub documentation could be exploited to achieve remote code execution on the MCP host.

    MCP and LLM Security Research Briefing | Wiz Blog
  3. Reported Apr 17, 20252y ago

    Wiz makes its MCP Server available in private preview

    Wiz announced that its MCP Server for Wiz was available in private preview.

    MCP and LLM Security Research Briefing | Wiz Blog
  4. Reported Apr 17, 20252y ago

    Injection issues found in Anthropic MCP servers

    Researcher Guy Goldenberg found injection issues affecting Anthropic's MCP PostgreSQL and Puppeteer servers.

    MCP and LLM Security Research Briefing | Wiz Blog
  5. Reported Apr 17, 20252y ago

    Anthropic introduces the Model Context Protocol

    Anthropic introduced the Model Context Protocol (MCP) to connect LLM applications with external data sources and tools.

    MCP and LLM Security Research Briefing | Wiz Blog
Do you run this?Follow how adversaries are adapting to this technology, and where it touches your stack today.
Track This Risk
Mallory platform

See the full picture, correlated to your attack surface.

This page covers what’s public. Mallory adds the parts that aren’t: which of your assets are affected, which threat actors are using it right now, and what to deploy next.

Exposure mappingMap indicators from this story to your assets and identify affected systems in minutes.
Threat actor evidenceEvery observed campaign, victim, and pivot linked to actors named in this story.
Associated malwareMalware, exploits, and IOCs connected to the activity described here.
Detection signaturesYARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Scheduled alertsGet matching new stories delivered to your team as they break, not the next morning.
AI threadsAsk questions about this story and take action on the answers.