AI BriefingCloudflare Blog news
The latest AI and developer news from Cloudflare Blog, with short summaries.
Visit website →Supporting the Most Critical Missions: Cloudflare for Government Achieves FedRAMP Class D (High) Authorization
Cloudflare for Government has achieved FedRAMP High authorization, the highest security standard for the US government.
Analyzing Legitimate and Malicious Behavior in the Agentic Internet
Cloudflare analyzes continuous traffic behavior and trust scores to prevent bots and fraud.
Integrating Workers AI and AI Gateway into a Single AI Control Plane
Cloudflare is unifying entry points, observability, and billing for Workers AI and AI Gateway.
Cloudflare Announces Ambassadors and Community Engineers Programs, Adds $1 Million to Open Source Support
Cloudflare is revamping its community ambassador and engineer programs and providing an additional $1 million in support for open source.
Introducing Radar Researcher: An AI Tool for Exploring Internet Data in Natural Language
Cloudflare has launched the beta version of Radar Researcher, which analyzes internet data through natural language questions.
Provide WebMCP Interface to All Websites
Cloudflare released a developer preview that attaches WebMCP tools to websites without code changes.
Introducing Kitesurf: An Agent-First Browser Running on V8 Isolates in Cloudflare Workers
Cloudflare has released Kitesurf, a Workers-based browser optimized for AI agents.
Building an Open Agentic Internet: Read, Discover, Call, and Pay
Cloudflare has proposed open internet standards for agents to read, call, and pay.
From Search Rankings to Recommendations: Preparing Sites for the AI Agent Era
Cloudflare has integrated tools into its dashboard to assess site accessibility and recommendation potential for AI agents.
Next-Generation Version of MCP
MCP has transitioned to a stateless protocol that requires no session or state storage.
Cloudflare AI Search: A Data Search Engine for Agents
Cloudflare introduced search capabilities for AI agents, public endpoints, and a predictable pricing model.
Cloudflare Named Sole 'Visionary' in 2026 SASE and SSE Reports
Cloudflare was named the sole Visionary in the 2026 SASE and SSE reports.
Agent Access Model
AI agents require real-time, task-level access controls instead of human-oriented permission models.
Rethinking Work with Cloudflare OS
Cloudflare has unveiled Cloudflare OS, an internal platform for safely leveraging AI agents.
WriteGuard: Granular Control for MCP Servers
Cloudflare has released WriteGuard to control and track write operations by MCP agents.
Cloudflare OS: An Open Platform for Agents, Apps, and Work
Cloudflare has open-sourced Cloudflare OS, an enterprise AI agent platform.
Detecting Anomalous AI Behavior via Identity-Aware Analytics
Cloudflare analyzes AI usage patterns by user and agent to identify anomalous behavior and cost spikes.
Building a Software Factory to Reduce Astro's GitHub Issues to Zero
Astro reduced its open GitHub issues from over 200 to approximately 30 using AI agent-based automation.
Now you can debug Workers with local tracing
Cloudflare automatically collects OpenTelemetry traces from local Worker invocations to support AI agent debugging.
Cloudflare Agents Unveiled
Cloudflare has unveiled Cloudflare Agents, which unifies the deployment and operation of AI agents.