Managed Agents can run on your own servers now. MCP keys still stay out of the sandbox.
By Lior AharonovFounder, 7IT Solutions ·
What happened
On 12 November 2026, Anthropic opened a private beta of self-hosted Claude Managed Agents: the full service, including sandboxes, credentials and session history, runs in the customer's own cloud or on premises. For MCP tools, a proxy outside the sandbox adds the credential to the request. Credentials can sit in the customer's own secrets manager.
Why it matters
Your MCP server may soon get calls from agents running behind a customer's own firewall. The agent never holds your token; a proxy outside the sandbox attaches it. And if your host is not on their allowlist, the call is blocked.
What to do
If you sell an MCP server to enterprises, publish the exact hostnames it calls so a customer can allowlist them, and test that it works when a proxy adds the credential to each request.

My take
Lior Aharonov
Founder, 7IT Solutions
The safest key is the one the agent never sees. Make sure your server is ready to meet that agent.
Sources
| Operate Claude Managed Agents inside your security perimeter | claude.com |
Researched with AI tools; every fact is checked against the linked sources.