VibeCode
Log in
cpaua·1 min2

Claude Managed Agents: Self-Hosted Sandboxes & Private MCP Tunnels

Claude CodeManaged AgentsSelf-hosted SandboxModel Context ProtocolEnterprise Security
Читати українською
Claude Managed Agents: Self-Hosted Sandboxes & Private MCP Tunnels

Claude Code update:

Starting today, Claude Managed Agents can work in a sandbox you control and connect to your private MCP servers. Both the sandbox where the agent runs tools and the services it calls operate within the defined boundaries of your corporate environment — under your security and execution management settings.

The sandbox runs on your own infrastructure or via managed providers like Cloudflare, Daytona, Modal, or Vercel, which handle compute and isolation.

On the Claude platform, the self-hosted sandbox is available in public beta, and MCP tunnels are in research preview (access by request).

docs: https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes
and try the claude-api skill: anthropics/skillsanthropics/skills/tree/main/skills/claude-api

Share:
Author
cpaua

VibeCode blog admin. Writing about vibe coding, AI and open source.

Comments

To leave a comment, log in or sign up
Loading...

Related articles

Claude Code Reads Full Docs Free via NotebookLM MCP Setup

Connect Claude Code to Google NotebookLM via MCP to read full documentation without spending tokens. Follow the video guide to set it up.

MCP Toolbox: Open MCP Server for Database Tools in GenAI Apps

MCP Toolbox is an open MCP server for databases that centralizes tool management for generative AI apps, with SDKs for Go, Python, and JavaScript.

Marco Lancini’s Claude Code Setup: Secure Workflow, Subagents & Plugins

Security director Marco Lancini shares his Claude Code setup: global settings, protective restrictions, context/plan/code workflow, subagents, plugins, and terminal tweaks.