> ## Documentation Index
> Fetch the complete documentation index at: https://docs.yasmina.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Comprehensive Motor Insurance

> Use an AI coding assistant to build your Comprehensive Motor Insurance integration.

## Introduction

Every page of this documentation is published in an AI-readable format, so an AI coding
assistant — Claude Code, Cursor, GitHub Copilot, or any tool that can fetch a URL — can
read the [Comprehensive Motor Insurance guide](/multi-provider-integrations/motor-insurance) and API
reference directly and scaffold the integration for you: authentication, OTPs, quotes,
photo uploads, policy issuance, and error handling.

You stay in control of the code. The assistant writes the first draft against our guide
and OpenAPI spec; you review it, test it in the [Sandbox environment](/environments), and
harden it before going live.

## What to feed your assistant

Point your assistant at these pages. Appending `.md` to any page URL returns that page as
plain Markdown.

| Resource                                  | URL                                                                      |
| ----------------------------------------- | ------------------------------------------------------------------------ |
| Comprehensive Motor Insurance guide       | `https://docs.yasmina.ai/multi-provider-integrations/motor-insurance.md` |
| Authentication guide                      | `https://docs.yasmina.ai/authentication.md`                              |
| Motor Insurance OpenAPI spec              | `https://docs.yasmina.ai/car-api-reference/openapi.json`                 |
| Index of every page (for broader context) | `https://docs.yasmina.ai/llms.txt`                                       |

## Connect over MCP

If your assistant supports the Model Context Protocol, connect it to our documentation
MCP server instead of pasting URLs — it gives the assistant search and retrieval tools
over the entire documentation site:

```text MCP server URL theme={null}
https://docs.yasmina.ai/mcp
```

<CodeGroup>
  ```bash Claude Code theme={null}
  claude mcp add --transport http yasmina-docs https://docs.yasmina.ai/mcp
  ```

  ```json Cursor (.cursor/mcp.json) theme={null}
  {
    "mcpServers": {
      "yasmina-docs": {
        "url": "https://docs.yasmina.ai/mcp"
      }
    }
  }
  ```
</CodeGroup>

## Ready-made prompt

Copy the prompt below into your assistant and let it read the docs before it writes any
code.

```text Prompt for your AI assistant theme={null}
You are helping me integrate Yasmina's embedded Comprehensive Motor Insurance
(Multiple Providers) into my platform.

Before writing any code, read these documents:
- Integration guide: https://docs.yasmina.ai/multi-provider-integrations/motor-insurance.md
- Authentication:    https://docs.yasmina.ai/authentication.md
- OpenAPI spec:      https://docs.yasmina.ai/car-api-reference/openapi.json

Then build a backend integration that:
1. Authenticates with OAuth 2.0 client credentials and reuses the token until
   it expires.
2. Requests a quote OTP for the customer, then requests quotes and presents
   them for selection.
3. Uploads the five required vehicle photos (front, back, right, left, chassis
   number) before issuing a comprehensive policy.
4. Requests an issue OTP and issues the policy with the selected quote.
5. Handles validation and error responses as described in the guide, and
   follows its best-practice and branding guidelines.

Use the Sandbox environment (https://sandbox.yasmina.ai). Read the client ID
and secret from environment variables, keep all Yasmina API calls on the
backend, and never expose the credentials or the access token to the browser.
```

## Tips for good results

* **Always start in Sandbox.** The flows mirror Production, but no real policies are
  issued — see [Environments](/environments).
* **Keep credentials server-side.** Yasmina APIs must be called from your backend; make
  sure generated code never ships the client secret or token to the browser.
* **Hold the assistant to the guide.** The best-practice and branding guidelines in the
  guide are integration requirements, not suggestions — ask the assistant to implement
  them, then verify it did.
* **Review before Production.** Treat the generated integration as a draft: run the full
  flow end to end in Sandbox and review the code before switching the base URL to
  Production.

Questions along the way? [Contact us](/contact) — we are happy to help.