> For the complete documentation index, see [llms.txt](https://k-ai.gitbook.io/knowledge-ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://k-ai.gitbook.io/knowledge-ai/get-started/mcp-quickstart.md).

# Quickstart — K-AI MCP

Five minutes to your AI agent answering questions on your K-AI knowledge. Works with Claude Desktop, Cursor, and Mistral Le Chat. Auth happens once via OAuth — a single sign-in grants access to every K-AI instance you're entitled to.

## Prerequisites

* A K-AI user account.
* One of: Cursor (≥ 0.42), Claude Desktop (latest), Mistral Le Chat (web).

## Install

{% tabs %}
{% tab title="Cursor (one-click)" %}
[**⚡ Install KAI Retrieval**](cursor://anysphere.cursor-deeplink/mcp/install?name=KAI%20Retrieval\&config=eyJ1cmwiOiJodHRwczovL2FwaS1yZXRyaWV2YWwua2FpLXN0dWRpby5haS9tY3AifQ==)\
\
[**⚡ Install KAI Audit**](cursor://anysphere.cursor-deeplink/mcp/install?name=KAI%20Audit\&config=eyJ1cmwiOiJodHRwczovL2FwaS1hdWRpdC5rYWktc3R1ZGlvLmFpL21jcCJ9)

Manual fallback — add to your Cursor MCP config (`~/.cursor/mcp.json` or `.cursor/mcp.json` in a project):

```json
{
  "mcpServers": {
    "kai-retrieval": {
      "url": "https://api-retrieval.kai-studio.ai/mcp"
    },
    "kai-audit": {
      "url": "https://api-audit.kai-studio.ai/mcp"
    }
  }
}
```

> **Note:** on some Linux distributions (notably Debian), `cursor://` deep-links may fail to open the app. Use the manual config if the buttons don't work.
> {% endtab %}

{% tab title="Claude Desktop" %}
Claude Desktop does not expose a public deep-link scheme for MCP installation. Add the connector through the web UI:

1. Open [claude.ai](https://claude.ai) and sign in (requires Pro, Max, Team, or Enterprise plan).
2. Click your profile icon > **Settings** > **Connectors**.
3. Click **+** then **Add custom connector**.
4. Add the server URL: `https://api-retrieval.kai-studio.ai/mcp`
5. Complete the OAuth flow in the browser popup.

To add the Audit MCP, repeat step 3 with URL `https://api-audit.kai-studio.ai/mcp`.

{% hint style="info" %}
Remote MCP servers must be added through the web UI Custom Connectors, not via `claude_desktop_config.json`. The config file is intended for local stdio servers only.
{% endhint %}
{% endtab %}

{% tab title="Mistral Le Chat" %}
Le Chat does not expose a public deep-link scheme. Add the connector through the web UI:

1. Open [chat.mistral.ai](https://chat.mistral.ai) and sign in.
2. Click the **toggle panel button** (sidebar).
3. Expand **Intelligence** > click **Connectors**.
4. Click **+ Add Connector** > select the **Custom MCP Connector** tab.
5. Fill in the form:
   * **Connector name:** `kai-retrieval`
   * **Connection server:** `https://api-retrieval.kai-studio.ai/mcp`
   * **Description:** K-AI document retrieval
   * **Authentication:** OAuth 2.1 (auto-detected)
6. Click **Connect** and complete the OAuth authentication flow.
7. In any chat, click the **Tools** button (four-squares icon) and enable the `kai-retrieval` connector.

> **Note:** Adding Custom Connectors may require Admin privileges on the Le Chat account.
> {% endtab %}
> {% endtabs %}

## First call

Once installed, in your client's chat: ask "What K-AI instances do I have access to?" The host LLM should call `retrieval_instances_list_available_instances` and report a list.

## Next steps

* Read the full [K-AI MCP overview](/knowledge-ai/k-ai-mcp/mcp.md).
* Try the [K-AI MCP cookbook](/knowledge-ai/k-ai-mcp/cookbook.md) (Recipe 1 — Find documents on a topic).
* Add the Audit MCP to your client too: [Connect a client](/knowledge-ai/k-ai-mcp/connect-a-client.md).