Agent Interoperability FAQs
- Updated: 2025/12/16
Review the FAQs to learn more about Agent Interoperability.
- Why not just use APIs?
- How do you take care of tools security for MCP inbound tool calling?
MCP clients are supported through centralized governance: RBAC and authentication (API keys).
- Every tool call is authenticated.
- Once a user is authenticated, we check if they are authorized to use certain automations. They can only access automations in the Control Room repository if they have the right permissions.
- Data security while in transit: All interactions between the MCP client and MCP server, and between the MCP server and the Automation Anywhere Control Room, are encrypted. We use TLS 1.2 encryption, which ensures all communication is secure.
- What is PRE-powered MCP, and how does PRE-integration help MCP?
Our MCP inbound interactions are powered by our Process Reasoning Engine (PRE). The PRE has a deep understanding of all the Automation Anywhere automations, processes, API Tasks, and AI Agents. It knows what they are and what they can do. When a user requests to use an MCP inbound tool from a third-party AI assistant, our PRE understands the user's intent and the context of the request. Then, it matches this with the unique automation in the Automation Anywhere repository.
- What license is needed to access Agent Interoperability?pYou can access Agent Interoperability with the Base platform license, which includes:
- Ability to use Automation Anywhere bots, processes, API Tasks, and AI Agents (if available in the Customer Control Room) as individual MCP inbound connections.
- RBAC is available for MCP Inbound connections.
- No limit to number of automations (bots and processes) that you can run.
- Streamable HTTP with API Key is supported.
When you add the Enterprise platform license, the PRE/Automation Discovery Service becomes available, in addition to what is offered in the Base platform license.