> For the complete documentation index, see [llms.txt](https://docs.insuraviews.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.insuraviews.com/ai-integrations/data-connector/setup/microsoft-copilot.md).

# Microsoft Copilot

Add the Insuraviews Data Connector to Microsoft 365 Copilot through a Copilot Studio agent.

Insuraviews works in Microsoft 365 Copilot and Teams through a Copilot Studio agent.

### Before you start

* Access to **Copilot Studio** in the Power Platform environment where the agent will live.
* No Power Platform data loss prevention (DLP) policy blocks the connector in that environment. MCP tools run as connectors, so DLP policies apply to them.

### Step 1: Create the agent

1. In Copilot Studio, select **Agents > New agent** (or **Create**) and name it, for example **Insuraviews Assistant**.
2. In the instructions, describe its job, for example *"Answer questions about insurance rate, rule, and form filings using the Insuraviews tool. Cite filings by state, company, and filing number."* Click **Create**.

### Step 2: Add Insuraviews

{% tabs %}
{% tab title="From the Microsoft marketplace" %}

1. Open the agent's **Tools** page and select **Add a tool**.
2. Search for **Insuraviews** and select it.
3. Select **Create a new connection**, sign in to Insuraviews and approve access, then select **Add to agent**.
   {% endtab %}

{% tab title="Using the connector URL" %}

1. Open the agent's **Tools** page and select **Add a tool > New tool > Model Context Protocol**.
2. Enter **Server name**: Insuraviews; **Server description**: *"Searches and retrieves US property and casualty insurance filings from Insuraviews (read-only)"*; **Server URL**: `https://mcp.insuraviews.com/mcp`.
3. For authentication, select **OAuth 2.0** and set **Type** to **Dynamic discovery**. No credentials are entered. Click **Create**, then **Next**.
4. Select **Create a new connection**, sign in to Insuraviews and approve access, then select **Add to agent**.
   {% endtab %}
   {% endtabs %}

Test the agent in the **Test your agent** pane before publishing.

### Step 3: Publish to Microsoft 365 Copilot and Teams

1. Click **Publish**.
2. Select **Channels > Teams and Microsoft 365 Copilot**, keep **Make agent available in Microsoft 365 Copilot** checked, and select **Add channel**.
3. Select **Availability options**. Share with specific people, or choose **Show to everyone in my org** and **Submit for admin approval**. A Teams admin approves it in the Microsoft 365 admin center.

### Using it (each user)

In Microsoft 365 Copilot, type **@Insuraviews Assistant** (or open it from Teams) and ask a question. The first time, sign in to Insuraviews and approve access.

### Test it

Ask: *"Using Insuraviews, which carriers filed the most homeowners rate filings in Texas in 2025?"*


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.insuraviews.com/ai-integrations/data-connector/setup/microsoft-copilot.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.