Startup News

Claude Agents Get Private Sandbox

Anthropic's Claude Managed Agents now offer self-hosted sandboxes and MCP tunnels, bringing agent execution and private service access under enterprise control.

StartupHub.ai Staff

By StartupHub.ai Staff, reviewed by Daniel Singer, Editor

2 min read

Claude Managed Agents in a private sandbox environment for secure tool execution
Securely run Claude Managed Agents in your own private sandbox with MCP tunnels.

Key facts

  • Anthropic's Claude Managed Agents now support self-hosted sandboxes for enhanced enterprise control.
  • New MCP tunnels allow agents to securely access private internal services without public exposure.
  • The move brings agent execution and tool usage entirely within customer-defined security perimeters.
Contents(3)

Anthropic is giving enterprises more control over its Claude Managed Agents. Starting today, the AI agents can execute within self-hosted sandboxes, keeping compute and sensitive data within a company's own infrastructure or managed provider environments.

This update also introduces Model Context Protocol (MCP) tunnels, enabling agents to connect to private servers and internal services without exposing them to the public internet.

Keep Agent Execution In-House

With self-hosted sandboxes, the sensitive files, packages, and services agents interact with remain within the enterprise's boundaries. While the core agent loop stays on Anthropic's infrastructure, the actual tool execution happens in a customer-controlled environment.

This allows organizations to leverage their existing network policies, audit logging, and security tooling. Compute resources are also under direct control, letting businesses allocate specific CPU, memory, and capacity for demanding tasks like builds or image generation.

Choose Your Sandbox Provider

Customers can bring their own sandbox clients or utilize supported providers. Cloudflare offers scalable sandboxes using microVMs and isolates with granular control over outbound requests and secrets injection. Daytona provides stateful, composable sandboxes accessible via SSH or authenticated URLs, designed for long-running tasks. Modal offers a cloud platform optimized for AI workloads, providing scalable compute and storage primitives. Vercel combines VM security with rapid startup times, integrating with cloud environments and managing credentials at the network boundary.

Secure Access to Private Services

MCP tunnels are designed for secure connectivity to internal resources. A deployed gateway establishes a single outbound connection, eliminating the need for inbound firewall rules or public endpoints. Traffic is encrypted end-to-end, ensuring that internal databases, private APIs, and knowledge bases can be safely leveraged as agent tools.

MCP tunnels are available in Managed Agents and the Messages API, managed via workspace settings in the Claude Console.

TopicsClaudeAnthropicAI AgentsSandboxingCloudflareDaytonaModalVercel

StartupHub.ai StaffDaniel SingerWritten by StartupHub.ai Staff, Editorial teamReviewed by Daniel Singer, EditorAbout

StartupHub.ai Staff, Editorial team

The staff writers of StartupHub.ai, ranging from investment analysts to avid AI tool users, early adopters and critical enthusiasts. Backgrounds span engineering, business and the arts. We hold every piece to rigorous standards of research and review.

Daniel Singer, Editor

Daniel Singer is an AI expert who has been writing about, covering and building AI technology since 2018.

More from Daniel Singer

Get the free daily brief every morning

Every morning the day's AI news, new AI startups and new funding rounds. Free and takes a few minutes to read, unsubscribe at any time.

Join 64,000 other subscribers.

Test your Agent Readiness now

Paste your website. How well ChatGPT, Claude and the other agents can read and use a site, in about a minute.

The videos behind the news, one flip at a time

The feed mixes the videos from our articles with startup demos and you flip through them like TV channels for free with no signup.