Cloudflare Accelerates AI Agent Development With The Industry's First Remote MCP Server
Cloudflare (NYSE: NET) has announced new offerings to accelerate AI agent development, including the industry's first remote Model Context Protocol (MCP) server. The company introduced three key components:
- Remote MCP server for enabling AI agents to interact with external services
- Free tier access to Durable Objects for building stateful applications
- Generally available Workflows for multi-step applications
The platform allows developers to build AI agents in minutes instead of months, providing scalable, cost-efficient solutions. Cloudflare's serverless platform automatically scales inference and AI agent resources based on demand, with GPU deployment across 190+ cities globally. The company's network ensures Durable Objects can scale to millions of simultaneous customer interactions while maintaining low latency.
Cloudflare (NYSE: NET) ha annunciato nuove offerte per accelerare lo sviluppo di agenti AI, inclusa la prima server remoto Model Context Protocol (MCP) del settore. L'azienda ha introdotto tre componenti chiave:
- Server MCP remoto per consentire agli agenti AI di interagire con servizi esterni
- Accesso gratuito a Durable Objects per costruire applicazioni con stato
- Workflows generalmente disponibili per applicazioni multi-step
La piattaforma consente agli sviluppatori di creare agenti AI in pochi minuti anziché mesi, offrendo soluzioni scalabili ed economicamente vantaggiose. La piattaforma serverless di Cloudflare scala automaticamente le risorse di inferenza e degli agenti AI in base alla domanda, con distribuzione GPU in oltre 190 città a livello globale. La rete dell'azienda garantisce che i Durable Objects possano scalare fino a milioni di interazioni simultanee con i clienti, mantenendo bassa latenza.
Cloudflare (NYSE: NET) ha anunciado nuevas ofertas para acelerar el desarrollo de agentes de IA, incluido el primer servidor remoto del Protocolo de Contexto de Modelo (MCP) de la industria. La compañía introdujo tres componentes clave:
- Servidor MCP remoto para permitir que los agentes de IA interactúen con servicios externos
- Acceso gratuito a Durable Objects para construir aplicaciones con estado
- Workflows generalmente disponibles para aplicaciones de múltiples pasos
La plataforma permite a los desarrolladores crear agentes de IA en minutos en lugar de meses, proporcionando soluciones escalables y rentables. La plataforma sin servidor de Cloudflare escala automáticamente los recursos de inferencia y de agentes de IA según la demanda, con implementación de GPU en más de 190 ciudades a nivel mundial. La red de la empresa asegura que los Durable Objects pueden escalar a millones de interacciones simultáneas con los clientes mientras mantiene baja latencia.
클라우드플레어 (NYSE: NET)는 AI 에이전트 개발을 가속화하기 위한 새로운 서비스를 발표했으며, 업계 최초의 원격 모델 컨텍스트 프로토콜(MCP) 서버를 포함합니다. 이 회사는 세 가지 주요 구성 요소를 소개했습니다:
- 외부 서비스와 상호작용할 수 있도록 하는 원격 MCP 서버
- 상태를 유지하는 애플리케이션 구축을 위한 내구성 있는 객체에 대한 무료 액세스
- 다단계 애플리케이션을 위한 일반 제공 워크플로우
이 플랫폼은 개발자가 몇 개월이 아닌 몇 분 만에 AI 에이전트를 구축할 수 있게 하여 확장 가능하고 비용 효율적인 솔루션을 제공합니다. 클라우드플레어의 서버리스 플랫폼은 수요에 따라 추론 및 AI 에이전트 리소스를 자동으로 확장하며, 전 세계 190개 이상의 도시에서 GPU를 배포합니다. 이 회사의 네트워크는 내구성 있는 객체가 수백만 개의 동시 고객 상호작용을 처리할 수 있도록 하면서 낮은 대기 시간을 유지합니다.
Cloudflare (NYSE: NET) a annoncé de nouvelles offres pour accélérer le développement d'agents IA, y compris le premier serveur distant du Protocole de Contexte de Modèle (MCP) de l'industrie. L'entreprise a introduit trois composants clés :
- Serveur MCP distant permettant aux agents IA d'interagir avec des services externes
- Accès gratuit aux Durable Objects pour créer des applications avec état
- Workflows généralement disponibles pour des applications à plusieurs étapes
La plateforme permet aux développeurs de créer des agents IA en quelques minutes plutôt qu'en plusieurs mois, offrant des solutions évolutives et rentables. La plateforme sans serveur de Cloudflare ajuste automatiquement les ressources d'inférence et d'agents IA en fonction de la demande, avec un déploiement de GPU dans plus de 190 villes à travers le monde. Le réseau de l'entreprise garantit que les Durable Objects peuvent évoluer pour gérer des millions d'interactions client simultanées tout en maintenant une faible latence.
Cloudflare (NYSE: NET) hat neue Angebote zur Beschleunigung der Entwicklung von KI-Agenten angekündigt, darunter den ersten Remote Model Context Protocol (MCP) Server der Branche. Das Unternehmen stellte drei wichtige Komponenten vor:
- Remote MCP Server, um KI-Agenten die Interaktion mit externen Diensten zu ermöglichen
- Kostenloser Zugriff auf Durable Objects zur Erstellung zustandsbehafteter Anwendungen
- Allgemein verfügbare Workflows für mehrstufige Anwendungen
Die Plattform ermöglicht es Entwicklern, KI-Agenten in Minuten statt in Monaten zu erstellen und bietet skalierbare, kosteneffiziente Lösungen. Die serverlose Plattform von Cloudflare passt die Ressourcen für Inferenz und KI-Agenten automatisch an die Nachfrage an, mit GPU-Bereitstellungen in über 190 Städten weltweit. Das Netzwerk des Unternehmens stellt sicher, dass Durable Objects auf Millionen gleichzeitiger Kundeninteraktionen skalieren können, während die Latenz niedrig bleibt.
- First-to-market with remote MCP server technology
- Introduction of free tier for Durable Objects
- Global GPU deployment across 190+ cities
- Pay-per-use pricing model reduces costs
- Platform enables rapid AI agent development (minutes vs months)
- None.
Insights
Cloudflare's introduction of the industry's first remote Model Context Protocol (MCP) server represents a significant technical advancement in the AI agent ecosystem. By enabling AI agents to directly interact with external services over the internet, Cloudflare has effectively shifted the paradigm from instructional AI to autonomous task execution.
The technical innovation here lies in making MCP remotely accessible rather than device-bound. This solves a critical scalability challenge that had been limiting mainstream adoption. By hosting MCP servers on their global network spanning 190+ cities, Cloudflare ensures persistent user experiences with minimal latency—keeping responses within 50ms of 95% of internet users.
Making Durable Objects available on the free tier is particularly noteworthy as it democratizes access to stateful serverless computing—essential for contextually aware AI agents. Combined with the general availability of Workflows for multi-step applications, Cloudflare has assembled the three core components needed for agentic systems: reasoning (AI models), execution (workflows), and access (APIs).
Their serverless, demand-based scaling approach addresses the unpredictable nature of AI inference workloads, eliminating the need to provision for peak capacity. This technical architecture creates a compelling advantage over traditional cloud providers that require constant provisioning regardless of actual usage patterns.
This product launch strategically positions Cloudflare to capture market share in the emerging AI agent economy. By introducing the complete infrastructure stack needed for AI agent development, Cloudflare is leveraging its existing network advantage to expand into high-growth AI services.
The business model innovation here is particularly compelling—their serverless platform with usage-based pricing reduces the financial barriers to AI deployment. Traditional hyperscalers force organizations to provision for peak capacity, creating significant cost inefficiencies. Cloudflare's approach of scaling from zero to global in milliseconds enables more predictable costs directly tied to actual usage.
The partnerships with Auth0, Stytch, and WorkOS for authentication demonstrate Cloudflare's ecosystem strategy, creating a more complete solution while addressing security concerns that often hamper AI adoption. Making Durable Objects available on the free tier represents a classic land-and-expand strategy to drive developer adoption.
From a competitive standpoint, claiming the "industry's first remote MCP server" gives Cloudflare first-mover advantage in a potentially lucrative market segment. Their existing network infrastructure provides a defensive moat against competitors trying to replicate their low-latency global reach. By focusing on enabling developers to "build agents in minutes, rather than months," Cloudflare is targeting productivity gains that create measurable ROI for customers—essential for driving enterprise adoption beyond experimental use cases.
Cloudflare’s Developer Platform and global network are the best place to build and deploy AI agents, removing cost and complexity barriers to making AI agents a reality
AI agents – AI-enabled systems that can act autonomously, make decisions, and adapt to changing environments – represent the future of AI. AI agents have the potential to unlock massive productivity gains, and yet businesses are struggling to build agents that deliver real return on investment. Building agents requires access to three core components: AI models for reasoning, workflows for execution, and APIs for access to tools and services. In order to build scalable agentic systems, organizations need access to a platform that can provide each of these components in a scalable, cost-efficient way.
“Cloudflare is the best place to build and scale AI agents. Period. The most innovative companies out there 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 was built for this moment. First, we built the most interconnected network on the planet. Then, we built a developer platform that took advantage of that network to run code within 50 milliseconds of
With today’s announcement, Cloudflare's Developer Platform addresses some of the most critical challenges in building AI agents by:
Unlocking smart, autonomous actions with the industry’s first remote MCP server
MCP is a fast-growing open source standard that lets AI agents interact directly with external services. This shifts AI from simply giving instructions to actually completing tasks on a user’s behalf – whether that’s sending an email, booking a meeting, or deploying code changes. Previously, MCP has been limited to running locally on a device, making it accessible to developers and early-adopters but hindering wider, mainstream adoption.
Cloudflare is making it easy to build and deploy remote MCP servers on Cloudflare, so any AI agent can securely connect over the Internet and interact with services, like email, without the need for a locally hosted server. MCP servers built on Cloudflare can retain context, providing a persistent, ongoing experience for each user. And through partnerships with Auth0, Stytch, and WorkOS, Cloudflare is simplifying authentication and authorization that allows users to delegate permissions to agents, making secure agent deployment dramatically simpler.
Building intelligent, contextually aware AI agents with Durable Objects, now on free tier
Previously only available as part of paid plans, developers can now access Durable Objects on Cloudflare’s free tier, expanding broad and democratized access to a critical component for building agents. Durable Objects are a special type of Cloudflare Worker that combine compute with storage, allowing you to build stateful applications in a serverless environment without managing infrastructure. Durable Objects provide the ideal foundation for AI agents that need to maintain context across interactions, such as remembering past preferences or changing behavior based on prior events. Cloudflare’s network ensures Durable Objects scale out to millions of simultaneous customer interactions and can operate agents near the original request, ensuring each customer has a fast, low latency response.
Deploying durable, multi-step applications with Workflows, now generally available
Workflows allows you to build multi-step applications that can automatically retry, persist, and run for minutes, hours, days, or weeks. Workflows is now generally available, providing developers and organizations with a reliable way to build and manage multi-step applications infused with AI. For example, building an agent Workflow to book a trip would require searching for flights in a price range, which would require a persistent search over a certain predetermined time span. Then, once the flights have been found, an agent would purchase the flights with traveler information and a credit card. And finally, send confirmation to each traveler in the party.
Paying only for what you use, for the most cost-efficient AI deployment
AI inference is hard to predict and inconsistent in nature, unlike training, because it relies on human behavior, including the time of day and what action a person wants to take. With traditional hyperscalers, this requires organizations to prepare and provision for the highest level of capacity they can expect, even if that level only happens at peak times. Cloudflare's serverless platform automatically scales inference and AI agent resources based on demand, from zero to global scale in milliseconds. This ensures organizations only pay for what they use, dramatically reducing costs compared to traditional cloud deployments that require constant provisioning.
"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."
Cloudflare has been a leader in making AI inference accessible, breaking down barriers that have kept AI out of reach for most businesses. Cloudflare has GPUs deployed across more than 190 cities globally, bringing AI as close to the user as possible for low latency experiences.
To learn more, please check out the resources below:
- Get started building at agents.cloudflare.com
- Blog: Piecing together the Agent puzzle: MCP, authentication & authorization, and Durable Objects free tier
- Blog: Cloudflare Workflows is now GA: production-ready durable execution
About Cloudflare
Cloudflare, Inc. (NYSE: NET) is the leading connectivity cloud company on a mission to help build a better Internet. It empowers organizations to make their employees, applications and networks faster and more secure everywhere, while reducing complexity and cost. Cloudflare’s connectivity cloud delivers the most full-featured, unified platform of cloud-native products and developer tools, so any organization can gain the control they need to work, develop, and accelerate their business.
Powered by one of the world’s largest and most interconnected networks, Cloudflare blocks billions of threats online for its customers every day. It is trusted by millions of organizations – from the largest brands to entrepreneurs and small businesses to nonprofits, humanitarian groups, and governments across the globe.
Learn more about Cloudflare’s connectivity cloud at cloudflare.com/connectivity-cloud. Learn more about the latest Internet trends and insights at https://radar.cloudflare.com.
Follow us: Blog | X | LinkedIn | Facebook | Instagram
Forward-Looking Statements
This press release contains forward-looking statements within the meaning of Section 27A of the Securities Act of 1933, as amended, and Section 21E of the Securities Exchange Act of 1934, as amended, which statements involve substantial risks and uncertainties. In some cases, you can identify forward-looking statements because they contain words such as “may,” “will,” “should,” “expect,” “explore,” “plan,” “anticipate,” “could,” “intend,” “target,” “project,” “contemplate,” “believe,” “estimate,” “predict,” “potential,” or “continue,” or the negative of these words, or other similar terms or expressions that concern Cloudflare’s expectations, strategy, plans, or intentions. However, not all forward-looking statements contain these identifying words. Forward-looking statements expressed or implied in this press release include, but are not limited to, statements regarding the capabilities and effectiveness of Cloudflare’s Developer Platform and Cloudflare’s other products and technology, the benefits to Cloudflare’s customers from using Cloudflare’s Developer Platform and Cloudflare’s other products and technology, the potential opportunity for Cloudflare to attract additional customers and to expand sales to existing customers through Cloudflare’s partnerships with Auth0 and Stytch, Cloudflare’s technological development, future operations, growth, initiatives, or strategies, and comments made by Cloudflare’s CEO and others. Actual results could differ materially from those stated or implied in forward-looking statements due to a number of factors, including but not limited to, risks detailed in Cloudflare’s filings with the Securities and Exchange Commission (SEC), including Cloudflare’s Annual Report on Form 10-K filed on February 20, 2025, as well as other filings that Cloudflare may make from time to time with the SEC.
The forward-looking statements made in this press release relate only to events as of the date on which the statements are made. Cloudflare undertakes no obligation to update any forward-looking statements made in this press release to reflect events or circumstances after the date of this press release or to reflect new information or the occurrence of unanticipated events, except as required by law. Cloudflare may not actually achieve the plans, intentions, or expectations disclosed in Cloudflare’s forward-looking statements, and you should not place undue reliance on Cloudflare’s forward-looking statements.
© 2025 Cloudflare, Inc. All rights reserved. Cloudflare, the Cloudflare logo, and other Cloudflare marks are trademarks and/or registered trademarks of Cloudflare, Inc. in the
View source version on businesswire.com: https://www.businesswire.com/news/home/20250407349544/en/
Cloudflare, Inc.
Daniella Vallurupalli
Vice President, Head of Global Communications
press@cloudflare.com
Source: Cloudflare, Inc.
FAQ
What are the key features of Cloudflare's (NET) new AI agent development platform?
How does Cloudflare's (NET) remote MCP server benefit AI development?
What cost advantages does Cloudflare (NET) offer for AI agent deployment?
How extensive is Cloudflare's (NET) GPU deployment for AI inference?
