Agents Can Provision Cloudflare Accounts via Stripe Projects
Cloudflare has partnered with Stripe to launch a protocol allowing AI agents to autonomously create accounts, manage billing, and register domains.
On April 30, 2026, Cloudflare expanded its infrastructure platform to allow AI agents to function as autonomous customers. Through a new partnership with Stripe, agents can now programmatically create Cloudflare accounts, register domains, manage paid subscriptions, and receive API tokens without human intervention in the dashboard. The release addresses a major bottleneck in automated software development by allowing systems to handle their own financial and infrastructural plumbing.
Autonomous Provisioning Architecture
The core of this release is the Stripe Projects protocol. By logging into Stripe and executing the stripe projects command via the Stripe CLI, agents can provision resources instantly. Cloudflare facilitates these actions through the release of the Code Mode MCP server and native Agent Skills.
These tools expose Cloudflare’s extensive API surface to agents running in environments like Cursor or Claude Code. The entire integration utilizes the Model Context Protocol to standardize the interaction. To preserve context windows for actual reasoning tasks, Cloudflare designed the toolset to consume under 1,000 tokens.
| Capability | Agent Action | Integration Mechanism |
|---|---|---|
| Account Creation | Instantiates a new tenant | Cloudflare Control Plane |
| Subscriptions | Starts paid plans like Workers Paid | Stripe Projects Plugin |
| Domain Registration | Searches, verifies, and buys domains | Cloudflare Registrar API (Beta) |
Security for these automated actions relies on a verification model requiring user consent. Users grant explicit permission for the agent to act, restricting the automated system to the exact permission boundaries of the authorizing human user.
Edge Infrastructure for AI Workloads
The provisioning capabilities concluded a broader platform update aimed at shifting edge computing away from human web traffic toward automated code execution. This included the introduction of Cloudflare Mesh, a private networking service that provisions shared private IP space for agents, Workers, and connected devices.
Cloudflare also launched Dynamic Workers, an isolate-based runtime engineered to sandbox and execute AI-generated code up to 100 times faster than traditional container deployments by leveraging millisecond startup times. To support the data requirements of these autonomous loops, the platform introduced Artifacts, a Git-compatible storage primitive built specifically for storing generated code at scale, alongside a private beta for managing persistent memory for agents across sessions.
Platform Adoption and Incentives
While the infrastructure protocol launched in partnership with Stripe, the architecture is platform-agnostic. Any platform managing authenticated users can integrate with Cloudflare to offer similar zero-friction infrastructure deployment. To accelerate immediate adoption, Cloudflare and Stripe are offering $100,000 in infrastructure credits to startups that incorporate using Stripe Atlas.
If you build autonomous coding systems, integrating the Stripe Projects protocol allows your agents to deploy applications completely end-to-end. You can instruct your coding agent to write the application logic, instantiate the necessary cloud routing, purchase an available domain, and deploy the live service in a single execution run.
Get Insanely Good at AI
The book for developers who want to understand how AI actually works. LLMs, prompt engineering, RAG, AI agents, and production systems.
Keep Reading
Build a Multi-Agent AI Code Review System with OpenCode
Learn how Cloudflare uses specialized AI agents and OpenCode to automate security, performance, and compliance reviews across thousands of repositories.
Google Launches Gemini Enterprise Agent Platform for AI Fleets
Google has replaced Vertex AI with the Gemini Enterprise Agent Platform, a centralized control plane for building and managing autonomous AI agent fleets.
Build Autonomous Tools 10x Faster via Claude Managed Agents
Anthropic debuts Claude Managed Agents, a cloud-hosted API suite that handles infrastructure, sandboxing, and persistent state for production AI agents.
Temporal Powers Mistral's New Workflows Orchestration Engine
Mistral launched a Temporal-backed orchestration layer to execute multi-step agentic systems with deterministic recovery and VPC support.
Anthropic AARs Hit 97% PGR in Weak-to-Strong Alignment Study
Anthropic's nine autonomous Claude Opus 4.6 agents achieved a 0.97 performance score in scalable oversight research, quadrupling the human baseline.