Review what's new and changed, and the limitations in Agent Interoperability for the v.39 release.

What's new

Support for MCP Inbound on Google Cloud Platform (GCP) Deployments

GCP customers can now use MCP inbound to securely trigger Automation Anywhere bots, processes, and API tasks from third-party AI applications, enabling direct agent-to automation execution in GCP-hosted environments.

Configure an MCP inbound tool
With the Model Context Protocol (MCP), third-party AI assistants can now safely trigger Automation Anywhere bots, processes, and API tasks. This expands automation across different agent systems. MCP support is powered by our Process Reasoning Engine (PRE). It smartly understands what the user wants and the special context of the request, making sure the right automation runs safely and effectively.

Agent Interoperability

Fixes

MCP Inbound Calls: Faster Synchronous Responses

MCP inbound calls now return an immediate synchronous response when the automation execution completes within 60 seconds. This applies to all automation types, including API Tasks, processes, bots, and AI Agents.

This enables you to build more responsive AI Assistants and real-time experiences by eliminating the need for repeated polling on short-running automations and reducing latency in conversational workflows.

Limitations

In Microsoft Copilot, if a user gets this error API call failed: Unauthorized: Please check your API token while listing the tools, they should try the workaround.

Workaround: Ask the customer to delete the existing tool and then re-add the same MCP connector using a new connection. Check if this solves the problem.

The MCP connection fails for users who have large repository dataset privileges in Microsoft Copilot and Enterprise Knowledge Platforms.
The DiscoverAutomation tool might not work or behaves unexpectedly if a user has access to more than 1,000 folders in the repository. This happens because the API times out when handling so many folders. Besides the DiscoverAutomation tool not working, there are no other problems.
When a user uses the DiscoverAutomation tool on public automations, the system only checks the first 200 automations that the user can access. This is based on the permissions set for them in the automation repository. Any automations beyond first 200 will not appear in the DiscoverAutomation's tool search results. However, the user can set up these specific automations as individual agent connections and use them as separate automation tools.
Checked-in automations might take a while to be discovered. It can take 5-10 minutes to summarize the automation. This depends on how many tasks are checked in and how long it takes to create the summary for each automation.
You must delete the agent connections manually whenever the associated automation is deleted or when the user's access is revoked. The MCP client might take some time to remove or refresh the deleted or revoked automations from Tools list because of caching.
You must manually refresh or edit the agent connections whenever you update any automation. This includes changes such as enhanced descriptions or when you add, update, or remove any input/output variables.