One Answer From the Customer Record and the Ledger

What you can do together

• Ask AI Intelligence Hub about a customer and get the case history and the financial record behind it in one answer, cited to each record.
• Have the documents filed against a record ingested and indexed, so a question about what was agreed is answered from the document itself with a citation.
• Draft a reply to a dispute or a service request from the record and the recorded call, shown to a person for approval before it goes back to Dynamics.
• Run a workflow over new cases that pauses at an approval node before any step that writes back or sends something.

How it connects

Dynamics 365 publishes an official MCP server, and AI Intelligence Hub connects to it as an MCP client. The server is configured once with a name, URL, transport and the headers that carry its credential; its tools are discovered when the connection is bound. In a workflow, an MCP node runs one named tool with arguments fixed at design time. For an agent, an MCP tool hands over the server's tool list, and the agent chooses a tool and fills the arguments as it works. The connection carries the credential it is configured with, so what an agent can read in Dynamics is bounded by what that credential is granted there. Retrieval from the library alongside it still runs under the asking user's own identity.

Where a step needs something the MCP server does not expose, the HTTP Request node calls the Dynamics REST API. In the other direction, the platform's REST API and a workflow's HTTP trigger are the inbound paths, so automation on the Dynamics side can start a workflow.

An ingestion connector pulls the documents held against Dynamics records into the library, where they are indexed with everything else. Fitting the connector to your instance is integration work against the published API, done per engagement rather than as a product change. Customer and financial records themselves stay in Dynamics and are read at query time.