Rearchitecting technology customer experience for the MCP generation
AI is transforming how technology companies serve customers, support users, empower employees, and operate across increasingly complex digital environments. But one question stands above the rest: Who controls the future of your customer and employee experiences, your company or your technology vendors? At Avaya, we believe the answer should be you. That is why we are embracing the open future of AI, building the Avaya Infinity® platform to support Model Context Protocol (MCP). It is the right move for technology companies that need to innovate quickly without abandoning trusted systems, proprietary data, established workflows, or the security and governance requirements that protect customers and intellectual property.
What is MCP?
MCP (Model Context Protocol) is an open standard that lets AI models like GPT, Claude, or Gemini securely interact with external tools, APIs, data sources, and user context. For tech companies, it supplies AI with the structured context, such as customer, product, support, and account details - needed to work within existing systems, permissions, and workflows. This makes AI far more effective across support, sales, IT, product operations, and customer success where speed, accuracy, and trust are essential.
"This is not a 'wait-and-see' moment. Avaya believes the time to be intentional about building the definitive open orchestration engine for the modern enterprise is now."
David Funck, Chief Technology Officer, Avaya
How does MCP work?
MCP is built on a client → model → server architecture:
- The Client gathers context (user info, role, task, environment).
- The Model (e.g., Claude, GPT) receives the context and a list of available tools or actions.
- The Server hosts the tools (APIs, databases, etc.) and executes any actions the model requests.
All communication follows structured schemas so interactions can be interpretable, traceable, and governed, an important requirement when AI is interacting with customer data, proprietary technology, source systems, and business-critical workflows.
Avaya Infinity with MCP: Achieving AI-powered technology communications intelligence
Technology firms can now look past traditional dashboards to evaluate CX data, spot trends, and create real-time views. Customer experience, support, success, IT, and product teams can securely explore data while ensuring enterprise access controls remain intact.
Removing friction from technology AI with MCP
For too long, bringing AI into technology customer experience has meant choosing between two difficult options:
- Lock in to a single provider's closed ecosystem, limiting flexibility as AI models, products, customer expectations, architectures, and business strategies evolve.
- Create costly, one-off integrations across CRM, support platforms, product telemetry, subscription systems, knowledge bases, developer tools, identity platforms, data environments, and other applications.
This false choice slows innovation and adds complexity to technology environments that are already evolving rapidly. It can also fragment the experience for customers and employees when information is distributed across products, clouds, platforms, and business systems.
Enter MCP, an open, vendor-agnostic standard designed to help AI models interact with tools, data, and operational logic securely and at scale. Think of MCP as a universal connection layer for AI. Instead of building a different connection between every model and every technology system, organizations can create a standardized way for approved AI capabilities to access the context and tools they need. As the AI ecosystem evolves, this approach can give technology companies greater freedom to innovate while maintaining control over the systems, data, workflows, products, and customer relationships that differentiate their business.
MCP enables AI systems to operate with dynamic awareness of customer, employee, session, product, account, and technical context. For Avaya Infinity, this means AI models can deliver experiences informed by relevant information across complex technology environments. A technical support interaction could draw upon approved CRM, product telemetry, entitlement, knowledge, case history, and interaction data while respecting the permissions governing each source. That level of contextual intelligence can be especially valuable for technology companies managing thousands of customers, users, products, services, employees, workflows, integrations, and support interactions across multiple regions and channels.
Shaping the future of open AI for technology customer experience
Avaya is not just talking about open AI. We are actively helping shape open standards while bringing native MCP support to Avaya Infinity for secure, model-agnostic, enterprise-ready orchestration.
For technology companies, that creates three important advantages:
- Control: Gain more control over AI models and tools so you can select capabilities based on the requirements of each business or technical use case instead of the limitations of a single vendor.
- Governance: Strengthen interoperability and oversight across customer experience systems, enterprise data, workflows, applications, and AI so capabilities can be introduced responsibly.
- Future-readiness: Build an AI architecture designed for fast-changing technology environments where openness, security, scalability, interoperability, and long-term flexibility are essential.
Collaboration with Databricks
As part of our commitment to secure, scalable, and open AI, Avaya is collaborating with Databricks to bring enterprise-grade governance and data privacy capabilities to the MCP implementation within the Avaya Infinity platform.
For technology companies, this approach can help establish controlled access between AI and the structured and unstructured data distributed across products, applications, cloud environments, customer systems, and enterprise platforms.
With fine-grained access controls, audit logging, and governed integration with enterprise data sources, technology organizations can explore AI-powered customer and employee experiences while maintaining greater visibility into how information is accessed and used.
"Generative AI offers tremendous potential to transform customer experiences, and we are thrilled to collaborate with Avaya to help organizations quickly unify their data, simplify data and AI governance and security, and ultimately deliver AI that understands their business."
Heather Akuiyibo, VP of GTM Integration, Databricks
From fragmented technology systems to freedom with MCP
A typical technology company may have dozens or hundreds of tools and data sources, including CRM, customer support platforms, product telemetry, subscription management, entitlement systems, developer tools, identity services, knowledge bases, observability platforms, data environments, and workforce applications.
At the same time, multiple AI models, copilots, applications, and agents may need controlled access to those systems. Before MCP, connecting each system to each AI model could require its own point-to-point integration. As the number of systems and AI capabilities grows, so does the development effort, maintenance burden, complexity, and technical debt. MCP changes that paradigm by introducing a standardized intermediary layer. Instead of solving an increasingly complex N x M integration problem, technology companies can move toward a more scalable N + M model.
Each enterprise tool can expose approved capabilities through an MCP server, while AI models and applications connect through MCP clients. Once components can communicate through MCP, technology companies gain a more flexible foundation for connecting AI with existing and future systems. That can dramatically reduce redundant integration work while protecting investments already made in the technologies, platforms, products, and workflows that support customers today.
This matters because technology customer journeys rarely live in one application. A single support interaction may touch communications, CRM, case management, product telemetry, entitlement, subscription systems, identity, knowledge, engineering tools, and analytics. Avaya Infinity with MCP can help connect those technologies, insights, channels, and workflows so technology companies can modernize the experience without requiring the entire technology environment to be replaced first.
The potential ROI of MCP for technology companies
With MCP, Avaya Infinity users can unlock deeper business value by giving AI access to more relevant context and approved enterprise capabilities.
For technology companies, that can mean faster issue resolution, more informed support interactions, more proactive customer success, more efficient employee workflows, more natural conversations, and better continuity throughout the customer lifecycle.
MCP creates the foundation for generative and agentic AI that is not simply intelligent, but situationally aware of the customer, user, account, product, technical environment, service history, and permissions surrounding an interaction.
| Before MCP | After MCP | |
| Integration | Custom connectors between individual AI models and technology systems | A standardized MCP interface can work across models and approved enterprise tools |
| Deployment time | Long, expensive due to bespoke engineering | 50–70% faster, lower costs via reuse (quiq.com, Palma AI, Humanloop, aibase.com) |
| Data access | AI blind to system data, context lost | Full real-time context: CMS, CRM, EHR, ERP |
| Risk management | Employees manually search multiple systems to diagnose issues and understand customer needs | AI can help surface relevant technical and customer information earlier in the interaction or workflow |
The future of technology is open
Technology companies have spent years building the products, platforms, systems, data, intellectual property, expertise, and customer relationships that differentiate their businesses. They should not have to surrender control of those investments to participate in the AI era. The world's leading AI technology providers are increasingly embracing open, contextual approaches to AI. Avaya shares that vision.
By bringing MCP to enterprise customer experience, Avaya can help technology companies connect AI with the systems they already trust, adopt the models that best serve each use case, preserve greater control over their architecture, and continuously innovate as the AI ecosystem evolves. The future of technology customer and employee experience should not be defined by a closed technology stack. It should be defined by what your company can build next.
Learn how Model Context Protocol reinforces Avaya’s open AI strategy
Glossary
Full glossary of terms below.
| Term | Definition | Why It Matters for Technology Companies |
| MCP (Model Context Protocol) | An open protocol that standardizes how AI models interact with tools, APIs, and memory via structured context objects. | Creates a scalable way to connect AI with CRM, support, product telemetry, subscriptions, knowledge, developer tools, and other technology systems. |
| Context | A bundle of structured information passed to a model—such as user ID, session history, roles, time, or tool availability. | Helps AI understand the customer, user, account, product, technical environment, and situation surrounding an interaction. |
| Model | The generative AI (e.g., Claude, GPT-4, Gemini) that receives the MCP context and generates responses. | Gives technology companies flexibility to select different AI models based on performance, security, cost, technical, or use-case requirements. |
| Client | The application or interface (e.g., chat window, agent framework, customer portal) that gathers and sends context to the model. | Can include customer portals, support applications, employee desktops, virtual assistants, developer interfaces, and other digital experiences. |
| Server | The logic layer that hosts tools, APIs, functions, and data sources the model can use via MCP. | Creates a governed way for AI to interact with enterprise systems without giving models unrestricted access to proprietary or sensitive resources. |
| Tools | Discrete functions or APIs (e.g., “search knowledge base,” “check ticket status,” “update CRM”) exposed to the model via MCP. | Allows AI to move beyond conversation and assist customers and employees with real technical and business tasks. |
| Schemas | The structured definitions (in JSON or YAML) for how tools and context should be represented and passed to models. | Creates consistency between AI models and technology systems, making integrations easier to understand, govern, scale, and troubleshoot. |
| Memory | Persistent context retained across sessions (user history, preferences, past actions) provided to the model. | Can enable more continuous customer and support experiences so users do not have to repeatedly explain the same technical issue or business need. |
| Ephemeral Context | Short-lived, session-specific information (e.g., current task, temporary variables). | Helps AI remain focused on the immediate support or operational workflow without unnecessarily retaining temporary information. |
| Agent | An AI system that can take actions, invoke tools, and make decisions based on MCP context — often used in autonomous or semi-autonomous workflows. | Provides the foundation for controlled agentic AI that can assist with multi-step support, customer success, IT, and operational workflows. |
| Orchestration | Coordinating multiple steps, tools, and model outputs to achieve a higher-order business goal. | Helps technology companies connect customer interactions with the many platforms, applications, teams, and workflows required to complete complex journeys. |
| Observability | The ability to inspect what context was passed, what decisions the model made, and how tools were used. | Supports transparency, governance, troubleshooting, security, and oversight when AI interacts with customer, technical, and proprietary information. |
| Interoperability | The ability for different AI models and platforms to work with a shared structure of tools and context. | Gives technology companies greater flexibility to evolve their AI strategies without replacing established systems or becoming dependent on a single AI provider. |