> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.dialogue-ai.co/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.dialogue-ai.co/_mcp/server.

# claude.ai

> Connect to the corpus via claude.ai Connectors.

The easiest way to connect. Set it up once on claude.ai and it becomes available in every conversation — on web, desktop, and mobile.

> **Note**
>
> Connectors require a paid Claude plan (Pro, Max, Team, or Enterprise). Free accounts support one connector.

## Setup

### 1. Get your API key

Contact [ben@dialogue-ai.co](mailto:ben@dialogue-ai.co) to receive your API key.

### 2. Open Connectors settings

Go to [claude.ai](https://claude.ai) → click your profile icon (top right) → **Customize** → **Connectors**.

### 3. Add the connector

Click **"Add Custom Connector"**.

Enter the following:

| Field          | Value                                         |
| -------------- | --------------------------------------------- |
| Name           | `Consumer Intelligence`                       |
| MCP Server URL | `https://mcp.dialogue-ai.co/YOUR_API_KEY/mcp` |

Replace `YOUR_API_KEY` with your API key.

Click **Add**.

### 4. Enable it in a conversation

Connectors are toggled per conversation. To use it:

1. Open a new chat
2. Click the **"+"** button in the message input
3. Hover over **Connectors**
4. Toggle **Consumer Intelligence** on

### 5. Verify it's working

Ask Claude:

> "Use the get_corpus_overview tool."

Claude should return live statistics from the corpus — total comment count, breakdown by emotional register, life stage, and so on.

---

## Example prompts

> "What are UK consumers most worried about when it comes to life insurance?"

> "Give me the highest-liked quotes from people in the pre-retirement life stage."

> "Fetch this page and compare the copy against the corpus: [https://example.com](https://example.com)"