New Offerings Simplify and Speed Up AI Agent Deployment
Cloudflare has unveiled several new offerings aimed at accelerating the development of AI agents. These innovations include the industry’s first remote Model Context Protocol (MCP) server, generally available access to durable Workflows, and a free tier for Durable Objects. These advancements enable developers to build and deploy AI agents in minutes, rather than months, simplifying the process and reducing costs.
AI agents, which are AI-enabled systems capable of acting autonomously, making decisions, and adapting to changing environments, represent the future of AI. Despite their potential to unlock significant productivity gains, businesses have struggled to build agents that deliver a real return on investment. Building effective AI agents requires access to AI models for reasoning, workflows for execution, and APIs for accessing tools and services. Cloudflare’s new offerings provide these components in a scalable, cost-efficient manner.
“Cloudflare is the best place to build and scale AI agents. Period. The most innovative companies see that agents are the next big frontier in AI, and they’re choosing Cloudflare because we’ve got everything they need to move fast and build at scale on our Workers platform,” said Matthew Prince, co-founder and CEO of Cloudflare.
“Cloudflare is the best place to build and scale AI agents. Period.”
– Matthew Prince, Co-founder and CEO of Cloudflare
Key Features of Cloudflare’s New Offerings:
- Remote MCP Server: The first of its kind, this server allows AI agents to interact directly with external services, shifting AI from merely giving instructions to completing tasks on a user’s behalf. This innovation removes the need for locally hosted servers, making it easier for developers to build and deploy AI agents that can securely connect over the Internet.
- Durable Objects Free Tier: Previously available only on paid plans, Durable Objects are now accessible on Cloudflare’s free tier. These objects combine compute with storage, allowing developers to build stateful applications in a serverless environment. This is ideal for AI agents that need to maintain context across interactions, ensuring fast, low-latency responses.
- Workflows: Now generally available, Workflows enable the creation of multi-step applications that can automatically retry, persist, and run for extended periods. This is crucial for building complex AI agent applications, such as booking travel arrangements or managing customer interactions.
Cloudflare’s serverless platform also ensures cost-efficient AI deployment by automatically scaling resources based on demand, reducing the need for constant provisioning and lowering costs compared to traditional cloud deployments.
“Cloudflare offers a developer-friendly ecosystem for creating AI agents that includes a free tier for Durable Objects and serverless options for AI inference,” explains Kate Holterhoff, senior analyst at RedMonk. “These low-cost, easy-to-use options could empower more businesses to adopt and experiment with agentic AI.”
With GPUs deployed across more than 190 cities globally, Cloudflare continues to lead in making AI inference accessible, bringing AI as close to the user as possible for low-latency experiences.
