GoKawiilAnthropic is introducing two new features for Claude Managed Agents that give users more control over the security and privacy.
Claude Managed Agents now support MCP tunnels and self-hosted sandboxes
Anthropic unveiled Claude Managed Agents in April, greatly simplifying the work required to build and deploy cloud-hosted AI agents.
Earlier this month, Managed Agents went even further with new dreaming, outcomes, and multiagent orchestration features.
Now Anthropic is adding two additional new features for May: MCP tunnels and self-hosted sandboxes.
“Both the sandbox where an agent executes tools and the services it reaches run within the established boundaries of your enterprise, under your security and runtime controls,” Anthropic says.
The new MCP tunnels feature allows Claude Managed Agents users to route services through a private network.
With MCP tunnels, your agents reach MCP servers inside your private network without exposing them to the public internet. Internal databases, private APIs, knowledge bases, and ticketing systems become tools your agents can call. A lightweight gateway you deploy makes a single outbound connection, no inbound firewall rules, no public endpoints, and traffic encrypted end to end.
MCP tunnels is a limited research preview, so requesting access is required before getting started for now.
Meanwhile, the new self-hosted sandbox feature lets you easily set boundaries for Claude Managed Agents.
... continue reading