Skip to Content

OpenAI Register MCP Server Tools activity in Jitterbit Studio

Introduction

An OpenAI Register MCP Server Tools activity, using its OpenAI connection, registers a remote MCP server as a tool provider with OpenAI and is intended to be used as a target to consume data in an operation. Unlike the OpenAI Register Tools and Register Tools V2 activities, which register custom function-call tool definitions, this activity connects OpenAI directly to a remote MCP server so that server's tools become available to a chained Prompt V2 activity.

When the operation runs, Jitterbit stores the registered MCP server and its resolved tool list so any operation chained to run after this one automatically has access to the registered server's tools when it calls a Prompt V2 activity using the same chatId. Private agents store this in memory; cloud agent groups can persist it across operations using the Store chat context across operations (V2 activities only) setting in the OpenAI connection. You do not need to capture the Register MCP Server Tools response or pass the tool definitions explicitly to the subsequent Prompt V2 operation.

Note

This activity uses OpenAI's own MCP tool support to connect directly to a remote MCP server. It is independent of the MCP Client connector and does not consume output from the MCP Client connector's List Tools activity.

Supported OpenAI models

This activity can be configured to use one of these OpenAI models:

Create an OpenAI Register MCP Server Tools activity

An instance of an OpenAI Register MCP Server Tools activity is created from an OpenAI connection using its Register MCP Server Tools activity type.

To create an instance of an activity, drag the activity type to the design canvas or copy the activity type and paste it on the design canvas. For details, see Create an activity or tool instance in Component reuse.

An existing OpenAI Register MCP Server Tools activity can be edited from these locations:

Configure an OpenAI Register MCP Server Tools activity

Follow these steps to configure an OpenAI Register MCP Server Tools activity:

Step 1: Enter a name and specify settings

In this step, provide a name for the activity and specify the MCP server and model to use. Each user interface element of this step is described below.

Tip

Fields with a variable icon support using global variables, project variables, and Jitterbit variables. Begin either by typing an open square bracket [ into the field or by clicking the variable icon to display a menu listing existing variables to choose from.

  • Endpoint menu: If you have multiple endpoints of the same connector type configured, a menu at the top of the screen displays the current endpoint name. Click the menu to switch to a different endpoint. For more information, see Change the assigned endpoint in Configuration screens.

    • Edit endpoint: Appears when you hover over the current endpoint name. Click to edit the currently selected endpoint's connection configuration.

  • Name: Enter a name to identify the activity. The name must be unique for each OpenAI Register MCP Server Tools activity and must not contain forward slashes / or colons :.

  • Chat ID: Enter the chatId. If using a Prompt V2 activity to create a chatbot assistant, you can write the chatId returned in its response to a variable to be referenced here. If you don't provide a chatId, one is generated automatically; in that case the registered server applies only to a new conversation rather than any existing assistant.

  • Prompt text: Enter a prompt to send along with the registration request, for example to ask the model to list the available tools. If left blank, the default prompt List all available tools is used.

  • Model: Use the menu to select a supported OpenAI model. The default model is gpt-4.

  • MCP Server Label: Enter a label to identify the MCP server, for example github-mcp.

  • MCP Server URL: Enter the URL of the remote MCP server to register.

  • MCP Server Access Token: Enter the access token used to authenticate with the MCP server.

    Note

    The request schema also supports registering multiple MCP servers in a single call by providing a tools array, with each entry specifying its own server_label, server_url, and access_token. The MCP Server Label, MCP Server URL, and MCP Server Access Token wizard fields apply only to the first server in that array.

  • Save & Exit: If enabled, click to save the configuration for this step and close the activity configuration.

  • Next: Click to temporarily store the configuration for this step and continue to the next step. The configuration will not be saved until you click the Finished button on the last step.

  • Discard Changes: After making changes, click to close the configuration without saving changes made to any step. A message asks you to confirm that you want to discard changes.

Step 2: Review the data schemas

Any request or response schemas are displayed. Each user interface element of this step is described below.

  • Data schemas: These data schemas are inherited by adjacent transformations and are displayed again during transformation mapping.

    Note

    Data supplied in a transformation takes precedence over the activity configuration.

    The OpenAI connector uses the OpenAI Responses API. Refer to the API documentation for information on the schema nodes and fields.

  • Refresh: Click the refresh icon or the word Refresh to regenerate schemas from the OpenAI endpoint. This action also regenerates a schema in other locations throughout the project where the same schema is referenced, such as in an adjacent transformation.

  • Back: Click to temporarily store the configuration for this step and return to the previous step.

  • Finished: Click to save the configuration for all steps and close the activity configuration.

  • Discard Changes: After making changes, click to close the configuration without saving changes made to any step. A message asks you to confirm that you want to discard changes.

Next steps

After configuring an OpenAI Register MCP Server Tools activity, complete the configuration of the operation by adding and configuring other activities or tools as operation steps. You can also configure the operation settings, which include the ability to chain operations together that are in the same or different workflows.

To complete an MCP tool-calling workflow, chain a Prompt V2 operation to run after this one and configure it with the same chatId. Because Jitterbit stores the registered server's tools for use by that operation (in memory on private agents, or using the Store chat context across operations (V2 activities only) setting on cloud agent groups), the Prompt V2 operation receives them automatically with no additional mapping required.

Menu actions for an activity are accessible from the project pane and the design canvas. For details, see Activity actions menu in Connector basics.

OpenAI Register MCP Server Tools activities can be used as a target with these operation patterns:

To use the activity with scripting functions, write the data to a temporary location and then use that temporary location in the scripting function.

When ready, deploy and run the operation and validate behavior by checking the operation logs.