MCP Agent module
Model Context Protocol (MCP) is a way to securely connect AI language models with other applications. You configure MCP servers, which allow the AI model to access the application. You can then send a prompt to the AI model, and it can return information from the application.
For example, you could configure a MCP server to connect an AI model with Gmail. When you send the prompt “Give me my last 5 emails from Gmail,” it can access your Gmail and return the emails.
The Model Context Protocol (MCP) module allows you to process a user prompt using a language model and MCP servers.
For more information about MCP in Fusion scenarios, see Add an AI prompt to your scenario.
Access requirements
| table 0-row-2 1-row-2 2-row-2 layout-auto html-authored no-header | |
|---|---|
| Adobe Workfront package |
Any Adobe Workfront Workflow package and any Adobe Workfront Automation and Integration package Workfront Ultimate Workfront Prime and Select packages, with an additional purchase of Workfront Fusion. |
| Adobe Workfront licenses |
Standard Work or higher |
| Product | If your organization has a Select or Prime Workfront package that does not include Workfront Automation and Integration, your organization must purchase Adobe Workfront Fusion. |
For more detail about the information in this table, see Access requirements in documentation.
Prerequisites
- You must have configured any MCP servers that you intend to connect to.
- You must have an LLM key to the selected LLM (Large Language Model).
Model Context Protocol module and its fields
Process User Prompt
This action module processes a prompt, using the language model and MCP servers you specify.