> 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).


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://k-ai.gitbook.io/knowledge-ai/get-started/mcp-quickstart.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.