How to Query Live Outlook Data in Claude Desktop
Model Context Protocol (MCP) is an emerging, open-source standard for connecting LLMs with external services and data sources. Through MCP Servers, AI clients can perform actions like opening Jira tickets, posting Slack messages, committing GitHub branches and more. With CData MCP Server, these capabilities expand exponentially.
CData MCP Server provides schema-aware context to AI tools — whether you're using it for AI-assisted code generation in IDEs like Cursor, or for querying live data through chat interfaces like Claude Desktop.
In this article, we guide the reader through installing CData API Driver for MCP Server, configuring the connection to Outlook, and asking questions of the data in Claude Desktop.
Prerequisites
You need to download Claude Desktop (download) and create an account before continuing.
Overview
Here's a quick overview of the steps:
- Download and install the CData API Driver for MCP Server
- Configure the connection to Outlook
- Ask questions about the data in Claude Desktop
Step 1: Download and install CData MCP Server
- To begin, navigate to https://www.cdata.com/solutions/codeassist/ and download the CData API Driver for MCP Server.
- Find and double-click the installer to begin the installation.
- Follow the prompts to complete the installation.
When the installation is complete, you are ready to configure MCP Server by connecting to Outlook.
Step 2: Configure the connection to Outlook
- After installation, the MCP Server configuration wizard should open automatically.
NOTE: If the wizard does not open automatically, search for "CData MCP Server" in the Windows search bar and double-click the application.

- Click the dropdown menu in MCP Configuration > Configuration Name and select "
"
- Name the configuration (e.g. "cdataapi") and click "OK."
NOTE: This name is used as the name for the MCP server and as the prefix for all of the MCP Server's tools.
Connecting to Outlook
Using OAuth Authentication
Microsoft Graph API uses OAuth 2.0 for authentication. You must register an application in the Microsoft Azure Portal to obtain OAuth credentials (Client ID and Client Secret).
Obtaining OAuth Credentials
- Log in to the Azure Portal.
- Navigate to Azure Active Directory > App registrations.
- Click New registration to create a new application.
- Enter an application name and select the appropriate account types.
- Set the Redirect URI to your application's callback URL (e.g., http://localhost:33333 for desktop apps).
- Click Register to create the application.
- On the application overview page, copy the Application (client) ID - this is your OAuthClientId.
- Navigate to Certificates & secrets and create a new client secret.
- Copy the client secret value - this is your OAuthClientSecret.
- Navigate to API permissions and add the required Microsoft Graph API permissions:
- Mail.Read - For accessing email messages
- Contacts.Read - For accessing contacts
- Calendars.Read - For accessing calendar events
- Tasks.Read - For accessing To Do tasks
- offline_access - For obtaining refresh tokens
- Click Grant admin consent to grant these permissions.
Connecting with OAuth
After setting the following connection properties, you are ready to connect:
- AuthScheme: Set this to OAuth.
- InitiateOAuth: Set this to GETANDREFRESH. The CData API Profile for Outlook will automatically walk through the OAuth process in order to obtain the access token.
- OAuthClientId: Set this to the Application (client) ID from Azure Portal.
- OAuthClientSecret: Set this to the client secret value from Azure Portal.
- TenantId: Set this to your Azure AD tenant identifier (GUID or domain name like 'contoso.onmicrosoft.com').
- CallbackURL: Set this to the Redirect URI you specified in your app registration (e.g., http://localhost:33333 for desktop apps).
Example connection string
Profile=C:\profiles\Outlook.apip;AuthScheme=OAuth;InitiateOAuth=GETANDREFRESH;OAuthClientId=your_client_id;OAuthClientSecret=your_client_secret;TenantId=your_tenant_id;CallbackUrl=http://localhost:33333;
Enter the appropriate connection properties in the configuration wizard.
- Click "Connect" to authenticate with Outlook through OAuth.
NOTE: The configuration wizard should open your browser and ask you to sign into Outlook. If your browser does not open, close the configuration wizard and re-open the application using "Run as Administrator" (see below).
- Finally, click "Save Configuration" to save the configuration.
NOTE: This saves the configuration details to a separate file and updates the Claude Desktop configuration file (claude_desktop_config.json) to start MCP Server when the Claude Desktop client starts.
With MCP Server configured, you are ready to start asking questions of your live data from Claude.
Step 3: Ask AI for answers from live Outlook data
Now that we have installed MCP Server and configured a connection, we are ready to start with Outlook data in Claude Desktop.
- Open Claude Desktop. It may take a moment for MCP Server to start, but you will see the list of servers and tools available in the Claude interface (look for the settings icon below the prompt bar).
You can individually enable and disable specific tools by clicking on the server name.
- Now that you have connected, you can ask Claude questions about the Outlook data. For example: "Can you give me a quantitative analysis about my closed-won opportunities by industry?"
NOTE: Claude may need to explore the Outlook data to make sense of it before it can begin answering questions of the data. The tabular model presented by CData alongside the database tools available simplify the data exploration and analysis for an LLM.
Build with MCP Server. Deploy with CData Drivers.
Download MCP Server for free and give your AI tools schema-aware access to live Outlook data during development. When you're ready to move to production, CData Outlook Drivers deliver the same SQL-based access with enterprise-grade performance, security, and reliability.
Visit the CData Community to share insights, ask questions, and explore what's possible with MCP-powered AI workflows.