Bring Live MongoDB Atlas Data Into Microsoft 365 Copilot

The federated Copilot connector for MongoDB Atlas gives organizations a governed way to bring live operational data into the flow of work across Copilot experiences.

To operate efficiently, businesses require timely information about the systems that underpin their organizations. For example, they need to be able to answer questions like: Which incidents are open? Which orders are delayed? What fields and data types are present in the customer collection? The answers they need often live in operational applications built on MongoDB Atlas, while the questions are asked in the productivity tools people use every day.

To help close that gap, MongoDB is excited to introduce a federated Copilot connector for MongoDB Atlas. Now generally available, the connector enables users to ask Microsoft 365 Copilot questions about live data in MongoDB Atlas, bringing operational context into the same experience where people collaborate, analyze information, and make decisions.

The connector surfaces MongoDB Atlas data across Microsoft Copilot experiences, including Copilot Chat, Researcher in Copilot, Copilot Cowork, Microsoft Word, Excel, and Teams, with additional experiences planned to follow.

Bring operational data into the flow of work

The connector brings MongoDB Atlas to Microsoft Copilot through MongoDB’s managed remote Model Context Protocol (MCP) server. When a user asks a relevant question, Copilot can query Atlas in real time—instead of relying on a static copy of the data.

This creates a more direct path from a business question to the information needed to answer it, and helps users—who may not have MongoDB expertise—access and analyze live operational data through an AI assistant.

Now, business users can use conversational prompts to:

• Retrieve live business data without writing database queries.

• Find and filter customers, transactions, products, orders, content, or operational events.

• Get quick counts and key performance indicators, such as the number of delayed orders or high-value customers.

• Summarize and rank data to identify top categories, products, regions, trends, averages, and other business insights.

For example, a user might ask Copilot to summarize the open incidents in an Atlas cluster supporting a payments application, identify delayed orders, or describe the fields and data types in the customer collection for a loyalty service. By industry, a supply chain team can investigate inventory, shipment, and warehouse exceptions. A financial services team can explore customer records, fraud alerts, and transaction investigations. And a retailer can ask questions about orders, loyalty, customer service, and personalization.

The connector can also help power business copilots and agents. Organizations can ground Copilot and other AI assistants in current MongoDB Atlas data for customer service, sales, operations, and decision support, bringing live operational context into the workflows where teams already work.

Connect to live data without migrating or indexing it

Organizations using MongoDB Atlas do not need to migrate their operational data, re-platform their applications, or rebuild their integrations to use the connector.

To do so, an administrator simply approves and enables the connector in the Microsoft 365 admin center. Users then sign in, and their existing Atlas permissions carry through to each query.

MongoDB Atlas remains the system of record. The connector queries Atlas directly rather than indexing a copy of Atlas data into Microsoft 365, so the information returned to users reflects the current state of the underlying application data.

This federated approach helps organizations connect their productivity layer to operational data while keeping that data in the environment where it is managed.

Put governance into every interaction

Making operational data more accessible requires controls that organizations can understand and manage. The connector is designed to support that approach through:

• Permission-aware access: Each query runs as the signed-in user and honors the permissions already defined in MongoDB Atlas.

• Administrator control: Admins approve the connector and can manage deployment through the Microsoft 365 admin center.

• Read-only access: The connector is designed for read-only interaction with Atlas data.

• Auditability: Administrators can audit connector activity in Microsoft Purview.

• No separate search index: The connector queries Atlas on demand instead of indexing a copy of Atlas data in Microsoft 365.

Together, these controls give organizations a practical way to make operational information available through Copilot without giving up the governance model around the source data.

A foundation for more productive work

AI-powered productivity depends on access to relevant business context. By connecting Microsoft Copilot and other AI assistants to live MongoDB Atlas data through a federated connection, MongoDB and Microsoft are helping organizations make operational information easier to use without adding a data-movement project or another application to maintain. Users can get answers, summaries, and insights from live data through natural language, while technical teams retain control over the underlying systems and permissions.

For organizations already running MongoDB Atlas on Azure and Microsoft 365 Copilot, the connector provides a way to build on existing investments. Teams can explore high-value operational questions, validate measurable business outcomes, and develop repeatable patterns for bringing current data into everyday decisions.

The result is a simpler path from question to context to action—grounded in the systems organizations already use and governed by the permissions they already have.