Key takeaways

  • Oracle Cloud Fusion Applications Release 26A enables AI agents to work together securely across systems, helping turn isolated use cases into more automated workflows.
  • MCP brings authoritative external data to agents, while A2A protocol lets agents in Fusion Applications collaborate with other Oracle and third party agents.
  • MCP and A2A are implemented in Oracle AI Agent Studio with Fusion Applications security and role-based access controls, so you can expand AI adoption with confidence.

As AI agent deployments grow in scale and complexity, a common question is emerging: How do our agents and other agents work together in a way that is secure, governed, and genuinely useful to the business? Oracle Fusion Cloud Applications provides a direct answer to that question with interoperability capabilities included in Release 26A of AI Agent Studio.  These new capabilities can help you move beyond isolated agent deployments toward wide-scale AI adoption that helps your business put AI to work for employees.

Two distinct but complementary open standards are at the core of this approach: Model Context Protocol (MCP) and Agent-to-Agent (A2A) protocol. Understanding the distinction between the two can help scale AI efforts.

MCP for data retrieval

MCP allows an agent to securely access external tools or data sources in a structured way. Rather than relying on the general knowledge of a large language model, the agent can use MCP to retrieve authoritative information from a third-party system. For example, a financial management agent can use this protocol to pull foreign exchange rates from a service provider to complete a financial transaction. This ensures that the financial management agent remains in control while grounding its responses in accurate, up-to-date data from an authoritative third party outside of Fusion Applications.

A2A for agent collaboration

In contrast, A2A allows agents running in different systems to communicate securely so they can work together. With A2A, one agent can delegate tasks to another and then incorporate the output into a broader workflow. Those agents can work together across systems (i.e., agents deployed in Fusion Apps working with non-Fusion agents) to complete more complex, longer-running requests. For example, consider the Oracle Fusion Cloud HCM Interview Management Assistant that helps automate scheduling with candidates. In cases where a site visit is required, the Interview Management Assistant could use A2A to call a Navan agent or Amex GBT agent to coordinate flight and hotel bookings that align with the interview schedule, without the recruiter leaving the Fusion UI.

Agents in the flow of work

If your organization uses general purpose agents through collaboration tools like Slack or Microsoft Teams, it’s likely that employees use chat to navigate topics like vacation or expense policies. Since they are general-purpose by design, these agents are designed for helping employees navigate generic questions, often based on summarizations of static PDF documents with vacation or expense policies. However, these agents couldn’t provide answers that are specific to an individual’s vacation balance or pending expense report—until now.

A2A let’s general purpose agents “invite experts into the room” so users can interact with Fusion Applications AI agents directly through Microsoft Teams or Slack. For example, an agent accessed via Slack could use A2A to call a specialized agent deployed in Fusion Apps to help a user check their individual sick leave balance in Oracle Fusion Cloud HCM or the status of a pending expense report in Oracle Fusion Cloud ERP. This can provide a convenient way to increase the utility of chat-based AI deployments while offering end users a less fragmented experience.

Enterprise-grade trust

Fusion Applications implements both MCP and A2A with a rigorous approach to governance. Because these new capabilities are built into AI Agent Studio, every interaction inherits the enterprise-grade security model of Fusion Applications. Authentication is enforced consistently, and role-based access controls ensure that users only see the data they are entitled to access regardless of how or where they engage with an agent. This provides the confidence required for technical and compliance teams to move from small experiments to broad-based adoption.

In sum

The addition of MCP and A2A support in Release 26A creates new opportunities for you to expand the scope of AI deployments within Fusion Apps and beyond. MCP provides the “wiring” to connect agents deployed in Fusion Apps to external sources like databases and third-party applications. And A2A lets your Fusion Apps agents work together with other agents to complete more complex tasks. Check out these additional resources on AI in Fusion Applications to see how these new interoperability features can differentiate your AI strategy.

Related posts you might like

Get more information link

If you’re an Oracle customer and want to get new stories from The Fusion Insider by email, sign up for Oracle Cloud Customer Connect. If you’re an Oracle Partner and want to learn more, visit the Oracle Partner Community.