Anthropic is introducing two new features for Claude Managed Agents that give users more control over the security and privacy.
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.
With self-hosted sandboxes, you keep sensitive files, packages, and services in your own infrastructure or with a managed sandbox provider. The agent loop that handles orchestration, context management, and error recovery stays on Anthropic’s infrastructure, while tool execution moves to your own configured environment.
Self-hosted sandbox supports bringing your own sandbox client or using one of Anthropic’s partners: Cloudflare, Daytona, Modal, and Vercel.
Self-hosted sandboxes arrive as a public beta feature. You can learn more about both updates to Claude Managed Agents here.
Recent Anthropic news:
Separately, research scientist and OpenAI founding team member Andrej Karpathy has joined Anthropic after being independent for some time:
Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.
— Andrej Karpathy (@karpathy) May 19, 2026
FTC: We use income earning auto affiliate links. More.
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。