Skip to content
X · @dotey

Anthropic launches Claude Managed Agents beta; Michael Cohen explains secure third-party key management for agents

Anthropic 昨天刚发布 Claude Managed Agents 公测,API 团队的 Michael Cohen 的科普:Agent 要替用户操作第三方服务,怎么安全地管理这些账号密钥?

Anthropic added Vaults to the Claude Managed Agents beta to manage each end user's third-party credentials with a per-user vault_id and automatic injection at session runtime. The post shows a three-step flow—create a Vault, bind credentials to an MCP server address, and pass vault_id when creating a session—and prices CMA at token usage plus $0.08 per session-hour. The key design is isolation: credentials never enter Claude's context window, code runs in a sandbox, auth goes through a dedicated proxy, and the harness cannot access secrets.

Why it matters: This adds the missing implementation detail for Claude Managed Agents: third-party credential isolation. HKR-H/K/R all pass via a concrete security hook, reproducible vault_id flow, pricing, and a real operator pain point; impact stays at the developer integration layer, so it is

Read the original ↗Export Markdown