Early Access: The content on this website is provided for informational purposes only in connection with pre-General Availability Qlik Products.
All content is subject to change and is provided without warranty.
Skip to main content Skip to complementary content

Qlik MCP server - Preview

Add the analytics capabilities of Qlik Cloud into your own LLM projects and AI tools and services.

Qlik Model Context Protocol (MCP) server allows your LLM to connect to your Qlik Cloud tenant. Once connected, your LLM can access your Qlik Cloud resources. You can then use Qlik MCP server and its tools to call Qlik APIs and perform activities such as:

  • Searching for information from your available apps, data products, and datasets.

  • Analyzing available analytics apps.

  • Creating charts and sheets.

Warning note

By clicking Approve when connecting your LLM client to the Qlik MCP server, you will enable the Qlik Server to share your Qlik Cloud data ("Content") with a third-party system (like an AI tool). That system is not managed by Qlik, and your Content will be located, stored and processed under the third party’s control.

Information note

The use of the Qlik MCP server is subject to the terms of the Qlik API policy. For more information on the terms and limitations of the API policy, see API policy.

Information note

If you would like to participate in the preview of the Qlik MCP server, please fill out this form.

Requirements

To use the Qlik MCP with your preferred LLM client, you require the following user role permissions in Qlik Cloud:

  • MCP: Allowed

  • Tenant administrator

For more information, see Managing custom roles.

Connecting to Qlik MCP

This section outlines how to connect using some of the most common LLM clients:

  • OpenAI ChatGPT

  • Anthropic Claude Desktop

The connection must first be made by a tenant administrator. After that, any user in the tenant can connect and authenticate.

Connecting to ChatGPT

Connect to the Qlik MCP server by creating a remote connection in ChatGPT.

Information note

You must be on a ChatGPT Team, Pro, or Plus plan to connect to the Qlik MCP.

  1. In ChatGPT, under Admin Settings, create a connection.

  2. After Name, give your connection a name

  3. After MCP Server URL, enter <your tenant URL>/api/ai/mcp.

  4. Under Authentication, select OAuth.

  5. For the Client ID, enter 0bea8559a554c4d0de177952d8e57f62.

  6. For the Client Secret, leave the field empty.

  7. Click Create on your custom connector.

  8. Sign into your Qlik Cloud tenant.

  9. Click Approve.

    Warning noteBy clicking Approve, you will enable the Qlik Server to share your Qlik Cloud data ("Content") with a third-party system (like an AI tool). That system is not managed by Qlik, and your Content will be located, stored and processed under the third party’s control.

Connecting to Claude

Connect to the Qlik MCP server by creating a remote connection in Claude.

  1. In Claude, open Settings.

  2. In Connectors, click Add custom connector.

  3. Enter a name for the custom connector, such as Qlik MCP.

  4. For the Remote MCP server URL, enter <your tenant URL>/api/ai/mcp.

  5. Under Advanced settings, in OAuth Client ID, enter 76d3f46e87655a50424bec7e0f0bb1e2.

  6. For the OAuth Client Secret, leave the field empty.

  7. Click Add.

  8. Click Connect on your custom connector.

  9. Sign into your Qlik Cloud tenant.

  10. Click Approve.

    Warning noteBy clicking Approve, you will enable the Qlik Server to share your Qlik Cloud data ("Content") with a third-party system (like an AI tool). That system is not managed by Qlik, and your Content will be located, stored and processed under the third party’s control.

Connecting to other LLM clients

You can connect other LLM clients to the Qlik MCP server. First a tenant administrator must create an OAuth token for the client. Then you add the Qlik MCP server as a remote connection.

Creating OAuth tokens for LLM clients

  1. In the Administration activity center, go to OAuth.

  2. Click Create new.

  3. For the client type, select Native.

  4. In the dialog, enter a name for the OAuth client.

  5. Optionally, add a description.

  6. Under Scopes, select user_default.

  7. Under Add redirect URLs, enter the authentication callback URL for the LLM client and click Add.

    For example, this is https://chatgpt.com/connector_platform_oauth_redirect for ChatGPT or https://claude.ai/api/mcp/auth_callback for Claude.

  8. Click Create.

  9. Copy the Client ID.

    It will be used to connect to the Qlik MCP server.

  10. Click Done.

Connecting to the Qlik MCP server

The section offers general guidelines for adding the Qlik MCP server to an LLM client. Specifics will vary depending on your LLM client.

  1. In your LLM client, add a new remote connection.

  2. For the URL, enter <your tenant URL>/api/ai/mcp.

  3. For the Client ID, enter the Client ID of the OAuth token.

  4. Create the connection.

  5. Sign into your Qlik Cloud tenant.

  6. Click Approve.

    Warning noteBy clicking Approve, you will enable the Qlik Server to share your Qlik Cloud data ("Content") with a third-party system (like an AI tool). That system is not managed by Qlik, and your Content will be located, stored and processed under the third party’s control.

Qlik MCP tools

The Qlik MCP server includes tools that let your LLM client perform actions for you in your Qlik Cloud tenant. You can customize your experience by selecting which Qlik MCP tools you want available.

Access to MCP tools is controlled by your permissions. The Qlik MCP tool is authorized as the user connecting, which includes User Default permissions. While you need MCP: Allowed to use the Qlik MCP tools, you also need to have permission in Qlik Cloud to use the capabilities or content type used by the tools. For example, if you do not have permission to access lineage in Qlik Cloud, you cannot use the Qlik MCP tool Qlik get lineage.

Users will be able to access content based on the User Default permissions. Depending on permissions, some tools may respond with no access.

Tool availability can also be limited by your tenant's licensing.

Information noteThe timeout for the Qlik MCP server is 6 hours.

The available MCP tools include:

  • Analytics: 
    • Qlik select values

    • Qlik search apps

    • Qlik list sheets

    • Qlik list measures

    • Qlik list dimensions

    • Qlik get sheet details

    • Qlik get current selections

    • Qlik get chart info

    • Qlik get chart data

    • Qlik describe app

    • Qlik create sheet

    • Qlik create measure

  • Dataset:

    • Qlik search datasets

    • Qlik get fields

    • Qlik get field values

    • Qlik get dataset schema

    • Qlik get dataset sample

    • Qlik get dataset profile

    • Qlik describe dataset

  • Lineage:

    • Qlik get lineage

  • Data product:

    • Qlik search data products

    • Qlik get data product

Limitations

The Qlik MCP server has the following limitations:

  • A tenant's Qlik MCP server can have a maximum of 20 concurrent application sessions loaded into memory at one time. Any number of users can be connected to these applications. Connections to applications beyond 20 will fail.

Did this page help you?

If you find any issues with this page or its content – a typo, a missing step, or a technical error – please let us know!