> 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.md).

# Data Connector

The Insuraviews Data Connector lets your AI assistant answer questions directly from Insuraviews' database of more than 2 million structured property and casualty filings across all 50 states and DC. Ask in plain language, and the assistant searches Insuraviews, reads the relevant filings and attachments, and links every filing it cites back to the Insuraviews app.

The connector is built on the [Model Context Protocol (MCP)](https://modelcontextprotocol.io), the open standard supported by every major AI platform, so one connector works across all of them.

{% hint style="info" %}
**Connector URL:** `https://mcp.insuraviews.com/mcp`
{% endhint %}

### Supported platforms

| Platform                            | Who sets it up                                       | Guide                                                                                                       |
| ----------------------------------- | ---------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |
| Claude (Team, Enterprise, Pro, Max) | Organization Owner, or each user on individual plans | [Claude](https://docs.insuraviews.com/ai-integrations/data-connector/setup/claude.md)                       |
| ChatGPT (Business, Enterprise, Edu) | Workspace admin                                      | [ChatGPT](https://docs.insuraviews.com/ai-integrations/data-connector/setup/chatgpt.md)                     |
| Gemini (personal Google accounts)   | Each user                                            | [Gemini](https://docs.insuraviews.com/ai-integrations/data-connector/setup/gemini.md)                       |
| Gemini Enterprise                   | Google Cloud admin                                   | [Gemini Enterprise](https://docs.insuraviews.com/ai-integrations/data-connector/setup/gemini-enterprise.md) |
| Microsoft 365 Copilot               | Copilot Studio maker                                 | [Microsoft Copilot](https://docs.insuraviews.com/ai-integrations/data-connector/setup/microsoft-copilot.md) |
| Other MCP-compatible tools          | Each user                                            | [Other MCP clients](https://docs.insuraviews.com/ai-integrations/data-connector/setup/other-mcp-clients.md) |

### What you can ask

* "Which carriers filed the most homeowners rate filings in Texas in 2025?"
* "Summarize Progressive's latest personal auto rate filing in Ohio, including the overall rate impact."
* "Find filings that mention roof surfacing schedules in Florida since 2023."
* "Compare how State Farm and Allstate define water damage exclusions in their California homeowners forms."

### How it works

1. You ask your AI assistant a question that needs filing data.
2. The assistant calls the Insuraviews connector, which searches, counts, or retrieves filings and attachments.
3. Insuraviews returns the results, each with a link to the filing in the Insuraviews app.
4. The assistant summarizes, compares, or drafts from those results inside your AI platform.

The first time you use the connector, you sign in to Insuraviews and approve access. You see only the data your Insuraviews subscription includes.

### Read-only by design

The connector only reads. It never writes, uploads, or submits anything to Insuraviews, and the summaries and drafts your assistant produces stay inside your AI platform. See [Security and data handling](https://docs.insuraviews.com/ai-integrations/data-connector/it-and-security/security-and-data-handling.md).

### Requirements

* An Insuraviews subscription with the Data Connector add-on. Contact your [Insuraviews account team](mailto:sales@insuraviews.com) to enable it.
* An Insuraviews login for each user.
* A supported AI platform plan (see each setup guide).
* Network access to the Insuraviews hostnames.  IT teams can find the list in [Network and Sign-in](https://docs.insuraviews.com/ai-integrations/data-connector/it-and-security/network-and-sign-in.md)


---

# 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.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.
