Claude Managed Agents

Claude Managed Agents is a suite of composable APIs that handles the entire infrastructure layer (from secure sandboxing to tool execution) so you can build and deploy autonomous AI agents at scale.

Anthropic takes the operational headache out of agentic workflows by running Claude on its own secure, managed infrastructure instead of yours. Through four core primitives (agents, environments, sessions, and events), this service manages persistent containers, executes tools via native Model Context Protocol (MCP) integrations, and handles long-running asynchronous tasks. You define the skills, tools, and success criteria: Anthropic handles the sandboxing and state management for a flat rate of $0.08 per session hour plus standard token costs.

https://platform.claude.com/docs/en/managed-agents/overview