Digital Realty makes ServiceFabric Model Context Protocol available

Digital Realty said it made ServiceFabric® Model Context Protocol (MCP) available as a programmable control layer for Private AI environments across its global interconnection platform. The company framed the update as a way to extend infrastructure capabilities into an AI-focused control layer.

The announcement ties ServiceFabric MCP to AI Private Exchange (AIPx), described as the underlying architecture that includes patented policy and orchestration technology for programmable AI infrastructure. Digital Realty also said ServiceFabric MCP extends its platform into a programmable foundation across more than 800 Digital Realty and third-party data centers.

ServiceFabric MCP is presented as an emerging open protocol and open standard intended to help AI systems and agents interact securely with infrastructure, applications, and enterprise services through standardized interfaces. The protocol is described as supporting intent-based design and provisioning, real-time discovery and telemetry for throughput, latency, and link health, identity and access control via OAuth 2, and operations integration with agent-assisted diagnostics and troubleshooting hooks for Slack, Microsoft Teams, Splunk, and Datadog.

The company said ServiceFabric MCP and AIPx are being validated across internal deployments, enterprise AI environments, and partner ecosystem implementations, and that ServiceFabric MCP is operating on its own infrastructure environments using internal AI workloads and operational deployments. Digital Realty also cited the customer example of See All AI, which said ServiceFabric and its Borton campus connectivity supported its NVIDIA DGX B200 environment for secure movement of large imaging datasets and dynamic connectivity to cloud resources. “Our strategy is simple: provide the foundational infrastructure enterprises need for sustained AI workloads, while enabling flexible scale as demand grows. ServiceFabric MCP extends the foundation of AIPx with programmable controls and agent-ready interfaces, and our patent position reflects the long-term investment we’ve made in this architecture,” said Chris Sharp, Chief Technology Officer, Digital Realty. “Enterprise adoption of Private AI infrastructure has reached an inflection point. Production AI workloads now demand control over data movement, policy enforcement, and partner integration that public cloud APIs alone cannot deliver. Providers combining global footprint with programmable, agent-ready interconnection are well positioned to support this next wave of enterprise AI investment,” said Mary Johnston Turner, Research VP, IDC. “At See All AI, we are developing advanced medical imaging AI systems that demand both massive compute performance and highly scalable data infrastructure. Digital Realty's Borton campus and ServiceFabric provide the high-bandwidth, low-latency connectivity required to support our NVIDIA DGX B200 environment, enabling secure movement of large imaging datasets, dynamic connectivity to cloud resources, and the operational resiliency needed for production healthcare AI,” said T. Michael Thornton, Chief Executive Officer, See All AI. Digital Realty said over time its broader Foundation for AI architecture expected to extend beyond programmable networking into space, power, inventory, partner ecosystems, and sovereign deployment patterns.

Provided by Globe Newswire on behalf of Digital Realty Trust. Click to read original content.