This topic guides you through setting up Model Context Protocol (MCP) inbound tools within Control Room, allowing third-party AI assistants to securely trigger your automations, including processes, and AI エージェント.

With MCP inbound connectivity, Automation Anywhere can receive a request from third-party AI エージェント and third-party AI Assistants. Using MCP, an AI Agent can:

  • Get data from third-party systems.
  • Make decisions using company data.
  • Run and discover automations, AI エージェント or processes from the Control Room.

Prerequisites

Make sure you have set up the following:

  • Control Room repository permissions.
  • An MCP client: For example, Microsoft Copilot, ENTKB (Enterprise KB), or another MCP-compatible agent that can register an external MCP server and use tools. Each MCP client might support different MCP features, allowing for varying levels of integration with MCP servers. For a comprehensive list of supported MCP clients and latest features, click Feature support matrix.

Procedure

  1. Sign in to the Control Room.
  2. Navigate to AI > Agent connections. From the Agent connections page, you can view the list of agent connections and tools.

    Agent add

  3. To add a new agent connection, you can either:
    • Click + Add in the top right corner of the page, the select Inbound tool.
    • Alternatively, click the Create icon above the table.
  4. From the Add inbound tool page, click Browse to search for the automation (タスク Bot, API タスク or AI エージェント) from a list of folders and files.
  5. Click to select the automation you want and then click Choose.
  6. Configure Tool name and Description:
    • After selecting the automation, the Tool name and Description fields will be populated.
    • For Enterprise License with Process Reasoning Engine (PRE): These fields are automatically populated with AI-friendly content from PRE, which understands the automation's capabilities and purpose.
    • For Base License: These fields are automatically fetched from the repository. If no description exists in the repository, the field will be blank, but both fields are required.
    Note: You can review and update these descriptions directly within the agent connection context. This allows you to make them more suitable and AI-agent friendly without needing to check out, modify, and check in the automation itself.
    • Tool name (Required): Rename it to be AI-friendly and unique across all agent connections. It must be between 1-128 characters and only contain letters (A-Z, a-z), digits (0-9), underscore (_), hyphen (-), or dot (.). No spaces or special characters are allowed.
    • Description (Required): Keep it clear, action-oriented, and provide descriptive summaries for automations to improve how AI agents use them.
  7. Click Next.
  8. Manage Input and Output variables: The Variable details section displays all input and output variables for the selected automation. You can mark variables as required or optional. You can review and update descriptions for each variable directly in this interface, making them more suitable and AI-agent friendly.
    Note: If a mandatory variable is not provided by the third-party AI assistant, the MCP client will prompt the user to enter the missing value.
  9. Click Add to finalize the creation.
Your new inbound tool now appears in the Agent connections table with a connection status of Enabled.
Note:

If an automation is updated or deleted, then you must update or delete the agent connection manually.

Supported Input and Output Variable Data Types
  • From MCP Inbound for Task bots and API Tasks:
    • Input: String, Number, Boolean, List, Dictionary, DateTime, and Record
    • Output: String, Number, Boolean, List, Dictionary, DateTime, and Record
  • From MCP Inbound for processes:
    • Input: String, Number, Boolean, List, Dictionary, and DateTime
    • Output: No data types are supported for process output.