![\"Web](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/10\/Techbnical-blog-Banner.png\")
\nSales and business users often need quick access to CRM information such as customer names, telephone numbers, revenue, location, and account details.<\/p>\n
\nSales and business users often need quick access to CRM information such as customer names, telephone numbers, revenue, location, and account details.<\/p>\n
we will build a real world Account Assistant that connects Microsoft 365 Copilot to an existing ASP.NET Core REST API. The REST API queries the Microsoft Dataverse Account table and exposes an account-search operation through an OpenAPI definition.<\/p>\n
We will then use Microsoft 365 Agents Toolkit to create an API plugin for a declarative agent and make the API available to Microsoft 365 Copilot.<\/p>\n
Suppose a sales representative asks:<\/p>\n
“Find Contoso.”<\/p>\n
Instead of opening Dynamics 365 and manually searching the Account table, the user can ask the same question through the custom agent in Microsoft 365 Copilot.<\/p>\n
The agent identifies that an account-search operation is required, sends the search term to our API, and the API queries Dataverse.<\/p>\n
Before starting, make sure you have:<\/p>\n
Create a folder for the demonstration and create the ASP.NET Core Web API project.<\/p>\n
dotnet new webapi -n CustomerCreditApi<\/p>\n
Open the project in Visual Studio Code.<\/p>\n
The project contains the API code that will eventually sit between Microsoft 365 Copilot and Dataverse.<\/p>\n
![\"Create](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/10\/Technical-Blog-Image-1.png\")
<\/p>\n
The API was configured to connect to Dataverse using an application identity.<\/p>\n
The Dataverse service obtains an access token and calls the Dataverse Web API.<\/p>\n
The Account endpoint exposes:<\/p>\n
GET \/api\/account\/search?search=Contoso<\/p>\n
Run the project:<\/p>\n
dotnet run<\/p>\n
The API runs locally on:<\/p>\n
http:\/\/localhost:5041<\/p>\n
Test the endpoint:<\/p>\n
http:\/\/localhost:5041\/api\/account\/search?search=Contoso<\/p>\n
The API returns the matching Dataverse Account records.<\/p>\n
For example:<\/p>\n
![\"\"](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/10\/Technical-Blog-Image-2.png\")
<\/p>\n
Before exposing the API to Microsoft 365 Copilot, verify that the complete API \u2192 Microsoft Entra ID \u2192 Dataverse connection works locally.<\/p>\n
Create\/configure an application registration in the Microsoft Entra admin center \/ Azure portal and use:<\/p>\n
in the API configuration.<\/p>\n
For example:<\/p>\n
{\r\n\"Dataverse\": {\r\n\"Url\": \"https:\/\/your<\/a>url.api.crm.dynamics.com<\/a>\",\r\n\"TenantId\": \"<TENANT-ID>\",\r\n\"ClientId\": \"<CLIENT-ID>\",\r\n\"ClientSecret\": \"<CLIENT-SECRET>\"\r\n}\r\n}\r\n<\/pre>\nThe API uses these credentials to obtain an access token and call the Dataverse Web API.<\/p>\n
Run the API:<\/p>\n
dotnet run<\/p>\n
Then test locally:<\/p>\n
http:\/\/localhost:5041\/api\/account\/search?search=Contoso<\/p>\n
If the configuration and Dataverse permissions are correct, the API should return the real Account records from Dataverse.<\/p>\n
![\"\"](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/10\/Technical-Blog-Image-3.png\")
<\/p>\n
Step 4: Install and Configure ngrok
\n<\/strong><\/h3>\nNow that the API has been successfully tested locally, expose it through a public HTTPS endpoint so Microsoft 365 services can reach it.<\/p>\n
Start the API:<\/p>\n
dotnet run<\/p>\n
Then start ngrok:<\/p>\n
ngrok http 5041<\/p>\n
ngrok provides a public HTTPS URL:<\/p>\n
https:\/\/<your-ngrok-domain>.ngrok-free.dev<\/p>\n
The Account Search endpoint can then be accessed as:<\/p>\n
https:\/\/<your-ngrok-domain>.ngrok-free.dev\/api\/account\/search?search=Contoso<\/p>\n
Test this URL and confirm that it returns the same Dataverse data as the local endpoint.<\/p>\n
![\"\"](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/10\/Technical-Blog-Image-4.png\")
![\"\"](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/10\/Technical-Blog-Image-5.png\")
<\/p>\n
Step 5: Add the OpenAPI Definition and Connect the Toolkit to the Environment
\n<\/strong><\/h3>\nThe REST API is described using an openapi.json file.<\/p>\n
The OpenAPI definition describes the operation:<\/p>\n
GET \/api\/account\/search<\/p>\n
and its parameter:<\/p>\n
search<\/p>\n
The operation description is important because it helps the agent understand when the API operation should be used.<\/p>\n
For example:<\/p>\n
Search active Dataverse Account records by account name. Use this operation when the user asks to find, search, or look up an account.<\/p>\n
Using Microsoft 365 Agents Toolkit, create a Declarative Agent and add an action based on the existing OpenAPI description.<\/p>\n
The toolkit generates the plugin project containing the required configuration and manifest files.<\/p>\n
![\"\"](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/10\/Technical-Blog-Image-6.png\")
<\/p>\n
Step 6: Install Microsoft 365 Agents Toolkit<\/h3>\n
Now that the REST API is working and publicly accessible, the next component is the Microsoft 365 Agents Toolkit.<\/p>\n
Open Visual Studio Code and install:<\/p>\n
Microsoft 365 Agents Toolkit<\/p>\n
The toolkit is used to create and package the API plugin for the Microsoft 365 declarative agent.<\/p>\n
Instead of manually creating the plugin structure, the toolkit can generate the required project from an existing OpenAPI description.<\/p>\n
Keep both windows (dotnet run and ngrok) running.<\/p>\n
\n- Make sure your openapi.json is the corrected version. It should have “schemes”: [“https”], “host”: “untracked-napped-hydrant.ngrok-free.dev”, and the x-nullable fields (the file I gave you earlier).<\/li>\n
- Create the project.<\/li>\n
- Click the Agents Toolkit icon, then Create a New Agent\/App.<\/li>\n
- Select Declarative Agent.<\/li>\n
- Select Add an Action.<\/li>\n
- Select Start with an OpenAPI Description Document.<\/li>\n
- Select Browse and pick your json.<\/li>\n
- Tick GET \/api\/account\/search and click OK.<\/li>\n
- Choose a folder outside your API project<\/li>\n
- Name it AccountAssistant.<\/li>\n<\/ol>\n
![\"\"](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/10\/Technical-Blog-Image-7.png\")
<\/p>\n
Step 7: Enable Custom App Upload in the Microsoft 365 Admin Center<\/h3>\n
Before testing the custom agent in Microsoft 365, ensure that the environment allows custom application uploads and that the required Microsoft Copilot access is enabled for the test account.<\/p>\n
This is an administrative configuration step and does not require any changes to the API or application code.<\/p>\n
![\"\"](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/10\/Technical-Blog-Image-8.png\")
<\/p>\n![\"\"](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/10\/Technical-Blog-Image-9.png\")
<\/p>\n![\"\"](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/10\/Technical-Blog-Image-10.png\")
<\/p>\n![\"\"](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/10\/Technical-Blog-Image-11.png\")
<\/p>\n