As it continues to evolve its corporate structure and applies artificial intelligence (AI) to simplify its communications and collaboration portfolio to deliver next-generation customer and employee experiences, Avaya is integrating Model Context Protocol (MCP) into its Avaya Infinity CX platform.
Avaya sees the move as part of a strategic shift towards open AI orchestration, enabling organisations to build customer experience (CX) environments that create connections rooted in a deep, real-time understanding of customer history, intent and journey. It believes that combining MCP with Infinity’s workflow orchestration can accelerate the ability of enterprises to deliver hyper-personalised experiences without compromising speed, control or security.
Built on Edify, a contact centre as a service (CCaaS) and unified communications as a service (UCaaS) platform that Avaya acquired in 2024, Infinity CX combines on-premise and cloud workflows, giving users a choice of which functions to migrate to the cloud and which to keep on-premise.
MCP, created by Anthropic, is the open standard that allows AI models to securely and reliably interact with external tools, data sources, application programming interfaces (APIs) and user context. MCP acts as a universal translator that enables AI systems to work with different software applications seamlessly, meaning developers will no longer need to create custom interfaces between each AI model and the data source. One of the key benefits of this streamlining is that business customers themselves can now integrate AI systems within a matter of minutes, removing the need for chaotic and unscalable custom connectors.
Avaya said that unlike traditional “prescriptive” workflows, this innovation leverages MCP to enable large language models (LLMs) and agentic AI to interact dynamically, allowing for more flexible and personalised customer journeys. This approach, it added, empowers business users to configure workflows that can adapt and evolve beyond predefined paths, enhancing customer experience.
Infinity with MCP allows data to be pulled for customer needs from multiple databases in near real time. Prior to MCP, creating this capability would have taken weeks or months. Furthermore, usage is said to span “countless” industries. For example, MCP-based clinical decision support demonstrated a 28% improvement in diagnostic accuracy and a 32% reduction in the time to appropriate treatment.
“The largest and most complex organisations must be able to leverage new tools, models and technologies as the world realises the full potential of AI in real time,” said Avaya CEO Patrick Dennis. “That’s why we decided to accelerate what was an MCP moonshot, an innovation-first initiative, into our Infinity platform 2025 roadmap.”
Avaya chief technology officer David Funck said customers need AI that understands who it’s speaking to, what matters now, and how to align every response to their unique business logic and customer expectations.
“This is not a ‘wait-and-see’ moment,” he added. “The real value of MCP is the possibilities it unlocks for our customers – a reality that would otherwise have required hundreds of developers collaborating across myriad proprietary systems and vendors. Avaya Infinity users will be able to meaningfully use AI with their data and rich customer journey context to orchestrate workflows and deliver experiences that were mere concepts until now. We are committed to delivering the kind of openness organisations need today with an eye toward whatever may come next.”
Also as part of this initiative, Avaya is partnering with data and analytics provider Databricks to simplify and “democratise” data and AI, and to subsequently deliver enterprise-grade data security and governance at scale. As a result, it said, customers will have even more choice and flexibility in how they use AI and data to create enduring connections.
“Generative AI offers tremendous potential to transform customer experiences, and we are thrilled to collaborate with Avaya to help organisations quickly unify their data, simplify data and AI governance and security, and ultimately deliver AI that understands their business,” said Databricks’ vice-president of GTM integration, Heather Akuiyibo.
