@claudeai: Live from Code with Claude London: we're launching self-hosted sandboxes (public beta) and MCP tunnels (research previe…
Summary
Anthropic launches self-hosted sandboxes (public beta) and MCP tunnels (research preview) in Claude Managed Agents, enabling agents to run within the user's own perimeter with default security controls.
View Cached Full Text
Cached at: 05/19/26, 10:46 AM
Live from Code with Claude London: we’re launching self-hosted sandboxes (public beta) and MCP tunnels (research preview) in Claude Managed Agents. Run agents inside your own perimeter, with your security controls applied by default. https://t.co/cxvmk3feHp
Similar Articles
@modal: Modal is proud to now support @claudeai Managed Agents with Modal Sandboxes.
Modal announces support for Claude AI Managed Agents with Modal Sandboxes, enabling self-hosted agent execution with security controls, coinciding with Claude's launch of self-hosted sandboxes and MCP tunnels.
@AnthropicAI: New on the Engineering Blog: The access and permissions we grant agents should evolve with their capabilities. In our o…
Anthropic's engineering blog details how they contain Claude agents across products using sandboxing and access controls to cap the blast radius, sharing lessons from deploying Claude Code, Claude Cowork, and claude.ai.
How we contain Claude across products
Anthropic published a detailed engineering overview of the sandbox techniques used to contain Claude across its products including Claude.ai, Claude Code, and Claude Cowork, covering process sandboxes, VMs, filesystem boundaries, and egress controls. The article explains the rationale and technologies (gVisor, Seatbelt, Bubblewrap) and mentions the srt open-source tool.
@Scobleizer: Keep your agents in their own sandbox. Properly, so they don’t want to escape.
Announces the launch of Archal, an API that provides stateful sandbox environments for AI agents to run tests and perform CI and evaluations.
I open-sourced the "harness" layer for AI agents: run Claude Code/Codex/Gemini with governed MCP tools (browser, editor, secrets)
Open-sourced a desktop workspace that provides a governed runtime for AI coding agents, offering 100+ MCP tools, RBAC, and a self-evolving toolbox.