Claude Managed Agents get self-hosted sandboxes and MCP tunnels
By Steven Van ·
The additions let agents run in a customer's own infrastructure and reach internal services without exposing them publicly.
Claude Managed Agents now support self-hosted sandboxes and MCP tunnels, two security additions from Anthropic. Self-hosted sandboxes let an agent's execution environment run in a customer's own infrastructure or with a managed sandbox provider, rather than only in Anthropic's environment. MCP tunnels let an agent reach services sitting inside a customer's security perimeter.
Together these give teams running Claude agents on internal systems more control over where code executes and how it reaches internal services, without exposing those services publicly. Full details are in the announcement.
Claude
AI assistant by Anthropic — write, analyze, code, and create with one of the most capable large language models available.
View Claude →