Posts tagged "enterprise-security"

News May 20, 2026

Anthropic's MCP Tunnels Pull Credentials Out of Claude Agents

Self-hosted sandboxes and MCP tunnels let Claude Managed Agents call internal APIs and databases without carrying enterprise credentials in the agent context. What changed on May 19, the architecture Anthropic chose, and why it's a different bet from OpenAI's.

News March 19, 2026

MCP Is the Backdoor Your Zero-Trust Architecture Missed

The Model Context Protocol connects AI agents to enterprise tools — but it ships without authentication, authorization, or audit trails. With 7,000+ exposed servers and a growing list of CVEs, MCP has become the blind spot in your zero-trust perimeter. Here's what happened, what's at stake, and how to lock it down.