MCP Client Get Prompt (Beta) activity

Introduction

An MCP Client Get Prompt (Beta) activity, using its MCP Client connection, retrieves specific prompts from an MCP server and is intended to be used as a source to provide data in an operation.

Create an MCP Client Get Prompt (Beta) activity

An instance of an MCP Client Get Prompt (Beta) activity is created from an MCP Client connection using its Get Prompt (Beta) 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 Creating an activity instance in Component reuse.

An existing MCP Client Get Prompt (Beta) activity can be edited from these locations:

• The design canvas (see Component actions menu in Design canvas).
• The project pane's Components tab (see Component actions menu in Project pane Components tab).

Configure an MCP Client Get Prompt (Beta) activity

Follow these steps to configure an MCP Client Get Prompt (Beta) activity:

• Step 1: Enter a name and specify settings
  Provide a name for the activity and specify the prompt.

• Step 2: Review the data schemas
  Any request or response schemas are displayed.

Step 1: Enter a name and specify settings

In this step, provide a name for the activity and specify the prompt. Each user interface element of this step is described below.

• 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 MCP Client Get Prompt (Beta) activity and must not contain forward slashes (/) or colons (:).

• Choose prompt: You can specify a prompt using either of these two options: Inform prompt name manually or Select prompt from list.

  • Inform prompt name manually: Select this option to provide the name of the prompt in the MCP server. When this option is selected, this field is visible:

    • Prompt name: Enter the name of the prompt.

  • Select prompt from list: Select this option to choose from a list of prompts available in the MCP server. When this option is selected, this field is visible:

    • Select a Prompt: This section displays prompts that are available in the MCP server.

    • Selected prompt: After you select a prompt, it is listed here.

    • Search: Enter any column's value in the search box to filter the list of prompts. The search is not case-sensitive. If prompts are already displayed within the table, the table results are filtered in real time with each keystroke. To reload prompts from the endpoint when searching, enter search criteria and then refresh, as described below.

    • Refresh: Click the refresh icon or the word Refresh to reload prompts from the MCP server endpoint. This may be useful if prompts have been added to the MCP server. This action refreshes all metadata used to build the table of prompts displayed in the configuration.

    • Selecting a prompt: Within the table, click anywhere on a row to select a prompt. Only one prompt can be selected. The information available for each prompt is fetched from the MCP server endpoint:

      • Name: The name of the prompt.

      • Description: The description of the prompt.

    Tip

    If the table does not populate with available prompts, the MCP Client connection may not be successful. Ensure you are connected by reopening the connection and retesting the credentials.

• 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 MCP Client connector uses the Model Context Protocol. The schema nodes and fields are defined by the MCP server.

• Refresh: Click the refresh icon or the word Refresh to regenerate schemas from the MCP Client 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 MCP Client Get Prompt (Beta) activity, complete the configuration of the operation by adding and configuring other activities, transformations, or scripts 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.

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

MCP Client Get Prompt (Beta) activities can be used as a source with these operation patterns:

• Transformation pattern
• Two-target archive pattern (as the first source only)
• Two-target HTTP archive pattern (as the first source only)
• Two-transformation pattern (as the first or second source)

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.