Cloudflare has introduced several new tools and concepts to support the development of an "Agentic Internet," where AI agents can interact with web content and APIs more effectively. This initiative addresses challenges AI agents face with human-centric web interfaces, such as login pages and payment systems.
The goal is to create an environment that is readable, discoverable, callable, and payable for AI agents, moving beyond traditional web scraping methods.
Cloudflare Wallets provide AI agents with unique usernames for stable identification and a native payment method for APIs and content. This simplifies the onboarding process for agents, which often struggle with human-designed payment flows.
Kitesurf is a new cloud-hosted browser specifically designed for AI agents, operating within V8 isolates on Cloudflare Workers. Unlike traditional browsers, Kitesurf focuses on managing context windows, performance, token costs, and scalability, rather than visual elements.
WebMCP (Web Model Context Protocol) allows websites to expose structured tools for AI agents without requiring changes to the origin code. This enables agents to interact with web pages using explicit functions, such as `searchFlights` or `bookTicket`, making interactions faster and more reliable than traditional scraping. WebMCP is shipping experimentally in Chrome 146.
Cloudflare Computer is an open-source runtime that provides persistent, computer-like environments for AI agents. It leverages Cloudflare isolates and container sandboxes to optimize where code runs, aiming to improve scalability and efficiency for AI agent deployments.
Precursor is a client-side behavioral analysis engine that continuously evaluates user session interactions to detect sophisticated bots and AI agents. This shifts bot detection from static challenges to ongoing behavioral analysis, making it harder for advanced automation to mimic human users over time.
New Cloudflare One capabilities have been announced to identify and control Model Context Protocol (MCP) traffic generated by AI agents. These controls help administrators monitor agent activity and prevent unauthorized connections, addressing security risks associated with autonomous AI actions.
Cloudflare also announced an improved community program, introducing Cloudflare Ambassadors and Cloudflare Community Engineers. An additional $1 million in open-source funding has been allocated to support individuals who contribute to open-source projects that enhance the internet.
Radar Researcher, an AI tool, was introduced to allow users to query Cloudflare's Internet data using plain language and receive interactive charts. This makes extensive Internet traffic data more accessible without requiring expertise in data structure or API documentation.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
Cloudflare announced new Cloudflare One capabilities to identify and control Model Context Protocol (MCP) traffic generated by AI agents. These controls help administrators monitor whether AI agents are using approved paths to access tools and prevent unauthorized connections, addressing security risks posed by AI agents' autonomous and rapid actions.
Cloudflare launched a developer preview enabling websites to integrate WebMCP (Web Model Context Protocol) with a single dashboard switch, allowing AI agents to interact with web pages via structured tools. This development aims to improve the efficiency and reliability of AI agent interactions by providing explicit functions instead of relying on web scraping or UI automation.
Cloudflare held "Agents Week" to introduce new tools and concepts for building and supporting AI-native applications and an "Agentic Internet." The event covered infrastructure, development lifecycle, security, and analysis tools for AI agents, aiming to shape how software interacts with the internet.
Cloudflare introduced Precursor, a new client-side behavioral analysis engine that continuously evaluates user session interactions to detect sophisticated bots and AI agents. This development shifts bot detection from static challenges to ongoing behavioral analysis, making it harder for advanced automation to mimic human users over time.
Cloudflare introduced Cloudflare Computer, an open-source runtime providing persistent, computer-like environments for AI agents using a combination of isolates and container sandboxes. This aims to improve scalability and efficiency for AI agent deployments by optimizing where code runs.
Cloudflare introduced Kitesurf, a new cloud-hosted browser specifically designed for AI agents to navigate the web and complete tasks. This development provides AI developers with a specialized tool for building agentic software, addressing the unique requirements of AI web interaction compared to human browsing.
Cloudflare Radar introduced Radar Researcher, a new AI tool that allows users to query Internet data using plain language and receive interactive charts. This development aims to make Cloudflare's extensive Internet traffic data more accessible to a wider range of users without requiring expertise in data structure or API documentation.
Cloudflare announced an improved community program, introducing Cloudflare Ambassadors and Cloudflare Community Engineers, alongside an additional $1 million in open-source funding. This initiative aims to support individuals who promote Cloudflare within their communities and those who contribute to open-source projects that enhance the internet.
Cloudflare proposes an "Agentic Internet" to accommodate AI agents as a new type of web visitor, distinct from human users. This initiative aims to establish open standards and protocols for agents to interact with web content, focusing on readability, discoverability, callability, and payment mechanisms.
Cloudflare has launched Kitesurf, a new browser designed specifically for AI agents, which operates within V8 isolates on Cloudflare Workers. This development addresses the high resource consumption of traditional browsers like Chromium when used by AI models, providing a more efficient solution for agent-based tasks.
Cloudflare has released a developer preview of WebMCP integration, allowing websites to expose tools for AI agents without code changes to the origin. This enables AI agents to interact with websites more efficiently than traditional scraping, using a new browser standard shipping experimentally in Chrome 146.
Cloudflare introduced Cloudflare Wallets, a new service designed to provide AI agents with stable identities and a native payment method for interacting with APIs and content. This initiative aims to simplify the onboarding process for agents, which currently struggle with human-centric login and payment systems, thereby fostering the growth of agentic commerce.