Enterprise AI is rapidly moving beyond simple chat experiences into a world where agents can reason, decide, and take action across business systems. However, an AI agent is only as valuable as the systems it can securely interact with. This is where the combination of Oracle AI Agent Studio and Oracle Integration Cloud (OIC) MCP Server becomes particularly compelling.
With the emergence of the Model Context Protocol (MCP) as a standard approach for connecting AI agents to external tools and services, organizations no longer need to build fragile, custom integrations for every new AI use case. Oracle brings this capability into the enterprise stack by enabling AI agents to communicate with governed business processes exposed through OIC MCP servers.
Calling an OIC MCP Server from Oracle AI Agent Studio opens the door to a powerful business pattern: AI agents that can move from conversation to execution. Instead of limiting agents to answering questions, enterprises can empower them to invoke workflows, access operational data, trigger approvals, or orchestrate backend actions — all through a standardized and reusable integration layer.
The business value extends beyond automation. Organizations gain faster AI adoption, reduced integration complexity, and greater reuse of existing enterprise integrations. Teams can expose trusted business capabilities once through OIC and make them consumable across multiple agents and AI-driven workflows, avoiding duplicated development effort and inconsistent implementations.
Equally important is the security and governance model. Enterprise AI cannot rely on unrestricted tool access. Oracle’s approach emphasizes controlled connectivity through authenticated endpoints, credential management, and governed integration assets. By leveraging OIC’s enterprise-grade integration controls together with AI Agent Studio’s managed tool configuration, organizations can extend agent capabilities without compromising security, observability, or compliance expectations.
In this blog, we will walk through how to connect and call an OIC MCP Server from Oracle AI Agent Studio, explore the configuration steps involved, and demonstrate how this integration helps build secure, scalable and business-ready AI agent experiences.
I will use one one the OIC integrations that I created and exposed as MCP Server. If you haven’t already, I would highly recommend that you check the blog, Transforming OIC Projects into MCP‑Enabled AI Tools, before progressing with this content. In this blog I have demonstrated step-by-step process of developing an integration within Oracle Integration Cloud platform and how to convert the integration into an MCP enabled AI-tool.
As a quick recap, here is what we did. We created a Project in OIC. We enabled the project as an MCP server.
Then we created an integration and enabled that as a Tool within the AI Agent.
We will pick up from this step. We will call this AI-Enabled MCP Server from Oracle Fusion AI Agent Studio. On a high-level, the steps involved are as follows:
1. Create a Tool based on the OIC MCP Server
2. Create an Agent Team
3. Create an Agent
4. Publish AI Agents
So let us crack on!!!
Create Tools
To create the Tool, login to Oracle Fusion instance and navigate to Tools > AI Agent Studio. From the navigation-pane at the bottom, click on Tools.
Click on Add.
From the dropdown list, select Tool Type as ‘MCP’.
Type in a Tool Name. Tool Code should auto-populate from the tool name you enter. Enter a Description. Select the Product Family and Product. For this example, I’ll select FIN and Payables respectively, since we are fetching the invoice details from our MCP server.
In the Authorization section, we will need to add the authentication details for the MCP server. Click Add.
Enter the Instance URL. The instance URL will be the instance URL of the MCP server that we have configured within OIC. It’ll have the following form:
https://<NameOfServiceInstance>.integration.<region>.ocp.oraclecloud.com/mcp-server/v1/projects/<OICProjectName>/mcp
Assuming that you have successfully created the integration and exposed it as a MCP server, navigate to the OIC project, edit the project and copy the MCP Server endpoint URL.
Add the Instance URL. Transport Type defines the communication method. Two options are available.
- Server Sent Events (SSE): Enables real-time, one-way streaming of data from a server to a client.
- StreamableHTTP: Enables servers to independently handle multiple client connections using the HTTP POST and GET requests.
We will select StreamableHTTP as we will be using HTTP POST/GET requests.
Next, select the Credential Type as Client Credentials, as I’ll be using OAuth 2.0-based authentication and confidential applications using Client Credential Grant Type. I have explained how to create a Confidential Application to Connect to OIC using Client Credential Grant Type in this blog. I would recommend to use JWT if you are doing this in production instance.
Next, we need to add the Token URL. The token URL is in the format below. You will need to replace <idcs-domain-url> with your Oracle Cloud Infrastructure IDCS Domain URL.
<idcs-domain-url>/oauth2/v1/token
To get the OCI IDCS Domain URL, login to OCI Cloud Console, From the menu, navigate to Identity & Security > Domains. Select the correct domain. In my case, I’m using the Default domain. Copy the Domain URL.
Add the Token URL.
Next we need to add the Client Credentials Connection Configuration. This is in JSON format and is in the following format. We will hard-code the value for grant type:”client_credentials”, as the confidential application that we had configured uses grant type = client credentials. You need to get the values for Scope, Client ID and Client secret from the confidential application that you had created.
{"grant_type":"client credentials","scope":"<scope>","client_id":"<client-id","client_secret":"client-secret"}
To get the Client ID and Client secret, navigate to your domain under which you have created the confidential application and navigate to the Integrated applications tab. From the OAuth configuration tab, copy the Client ID and Client secret.
Scroll down to the Resources section, and copy both consumer::all and ic/api.
Replace the values that you have gathered and paste it under Client Credentials Connection Configuration. Click Update. On successful connection, the tools that you have added to the OIC MCP project will be displayed.
To test the tool, click on Tool Preview.
The Tool Preview window will pop-up. The integration that we created expects an input payload in the form of InvoiceNumber. I populate the input payload and click on Preview.
I see that the output payload has been returned. I can now confirm that the tool is working as expected. Close the preview window.
Select the AI-Enabled tool ( which in my case is called GETINVOICEDETAILS) and click Create.
We have successfully created the MCP tool.
Create Agent Team
Next step is to create the AI Agent Team. To create the AI Agent Team, navigate to the Agent Teams tab. and click on the Add(+) button.
Under the Details tab, provide a Name for your Agent Team. Agent Team Code should auto-populate. Under Family, select the pillar in which you want to create the Agent in. Select the Product. For this demonstration, I have used FIN and Payables for the Family and Product respectively. Since we are creating a supervisor agent, I will select the agent Type as Supervisor. Add a Description.
Under the LLM tab, you can select the Large Language Model you want to use for NLP. You can chose to use the default model(GPT-4.1 Mini). Note that this model is free to use.
Or you can chose from the list of other available LLMs. Note that there might be additional charges to use these models. I would highly recommend checking with your Oracle CSM on the usage costs, in case you want to use any of these models.
If you are using one of the paid models, you have the flexibility to restrict the usage.
Under the Security tab, you can specify who should have access to use this Agent Team. If you want to make this Agent Team available for all employees, make sure you enable ‘For all employees’ option.
Click on Create to create your Agent Team.
Add Agent to the Agent Team
Once you have created the Agent Team, next step would be to create the Agent. From the tools panel on the left, click on Agents, as highlighted in the screenshot below. Then click on New Worker Agent, as we want to create a worker agent for this demo. Based on your requirement, you can also chose to add a Supervisor Agent.
The Agent creation panel pops up. Enter the Agent Name, Agent Code, Family and Product. Enter a Description for the Agent. Use the Agent Persona and Role to set the character profile(tone, style, attitude, and behavioral patterns) of the agent.
Use Prompt section to instruct the agent about its tasks, roles and responsibilities. Add guidelines for agent responses.
I will leave default values for remainder of the tabs and click on Create. This will create the Agent. Note that we are yet to add our tool to the agent.
To add the tool, select Tools. From the left-hand pane, search for the tool that you created earlier, and add the tool. Click Add.
The tools window pops up. Click Add. Repeat these steps if you want to add more tools to the agent.
Notice that our tool has been added.
Next step is to publish the agent team. However, before publishing the agent team and making it available for business users, you need to test the agent. Click on the Debug button to bring up the chat panel.
The formatted output is presented to the user.
We have successfully tested the agent. Next step would be to publish the agent.
Publish Agent Team
To publish the agent team, click on the Publish button on the top-right-hand corner.
You should be able to verify the status from the Agent Teams page. Note that since we have created the Agent Teams from scratch, it has been tagged as a Custom Agent Team.
There you go, we have successfully created a custom AI Agent to call an Oracle Integration exposed as an MCP Server from Oracle AI Agent Studio.
Hope this was helpful. Happy Learning.
References
Leave a Reply