Cloudflare and Anthropic have integrated Claude Managed Agents with Cloudflare Sandboxes, allowing developers to run the Claude agent loop on Anthropic's platform while using Cloudflare for code execution, secure connectivity, and custom tooling. The integration provides enhanced security via customizable outbound proxies with zero-trust credential injection, sandbox observability with SSH access and metrics, lightweight V8 isolate-based sandboxes as an alternative to full microVMs for massive scale, and private service connectivity via Cloudflare Mesh and Workers VPC. Built-in tools include browser automation (Browser Run), email capabilities, image generation via Workers AI, and support for custom tools. A deployment template and onboarding guide are available on GitHub.
Table of contents
An overview of Claude Managed AgentsThe Cloudflare environmentEnabling agents at Internet scaleSecuring your agentic workloadsDoing more with the Cloudflare Developer PlatformClaude + CloudflareSort: