Claude Managed Agents adds self-hosted sandboxes and MCP tunnels for enterprise deployments. Self-hosted sandboxes run tool execution and workloads on customer-controlled infrastructure or managed providers, while Anthropic continues to handle orchestration, context handling, and recovery logic. This enables tighter control of network policies, audit logging, runtime configuration, and data residency, keeping repositories, files, and services inside existing infrastructure. Supported providers include Cloudflare microVMs with zero-trust networking, Daytona long-running stateful environments, Modal scalable AI-focused CPU/GPU workloads, and Vercel sandbox isolation with VPC peering and credential injection. MCP tunnels allow Managed Agents and the Messages API to reach private MCP servers via an outbound encrypted gateway connection without exposing them publicly.
"Anthropic has expanded its Claude Managed Agents platform with two enterprise-focused capabilities: self-hosted sandboxes and MCP tunnels. The release aims to address a recurring challenge in enterprise AI deployments, where organizations want to use autonomous agents but cannot allow execution environments or internal systems to leave their security perimeter."
"Self-hosted sandboxes, now available in public beta, allow tool execution to run on infrastructure controlled by the customer or through managed providers such as Cloudflare, Daytona, Modal, and Vercel. While Anthropic continues to manage orchestration, context handling, and recovery logic, the actual execution of tools and workloads happens within customer-controlled environments."
"The approach provides enterprises with better control over network policies, audit logging, runtime configuration, and data residency. It keeps repositories, files, and services within the existing infrastructure, allowing organizations to manage compute sizing and runtime images for resource-intensive tasks like long-running builds and image generation."
"Anthropic also introduced MCP tunnels, currently available in research preview. The feature enables Managed Agents and the Messages API to connect to private Model Context Protocol (MCP) servers without exposing them to the public internet. Instead of opening inbound firewall rules, organizations deploy a lightweight gateway that establishes an outbound encrypted connection to Anthropic infrastructure."
Read at InfoQ
Unable to calculate read time
Collection
[
|
...
]