home / mcp / qlik sense mcp server

Qlik Sense MCP Server

Bridges Qlik Sense Enterprise APIs with MCP clients to enable app discovery, scripting, analysis, and metadata access.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "bintocher-qlik-sense-mcp": {
      "command": "uvx",
      "args": [
        "qlik-sense-mcp-server"
      ],
      "env": {
        "LOG_LEVEL": "INFO",
        "QLIK_USER_ID": "your-username",
        "QLIK_HTTP_PORT": "443",
        "QLIK_PROXY_PORT": "4243",
        "QLIK_SERVER_URL": "https://your-qlik-server.company.com",
        "QLIK_VERIFY_SSL": "false",
        "QLIK_WS_RETRIES": "2",
        "QLIK_WS_TIMEOUT": "8.0",
        "QLIK_ENGINE_PORT": "4747",
        "QLIK_CA_CERT_PATH": "/absolute/path/to/certs/root.pem",
        "QLIK_HTTP_TIMEOUT": "10.0",
        "QLIK_USER_DIRECTORY": "COMPANY",
        "QLIK_CLIENT_KEY_PATH": "/absolute/path/to/certs/client_key.pem",
        "QLIK_REPOSITORY_PORT": "4242",
        "QLIK_CLIENT_CERT_PATH": "/absolute/path/to/certs/client.pem"
      }
    }
  }
}

You deploy and run the Qlik Sense MCP Server to bridge Qlik Sense Enterprise APIs with your own systems using the Model Context Protocol. It provides a unified interface for Repository and Engine API operations, supports certificate-based authentication, and enables you to discover apps, extract scripts, analyze data, and manage metadata through MCP tools.

How to use

You interact with the MCP server using an MCP client. Start by launching the server through your preferred runtime, then issue calls to the available tools to perform common analytics tasks. Typical workflows include listing all apps with their metadata, fetching detailed app information, extracting an app’s load script, retrieving field statistics, creating data analysis hypercubes, and enumerating app sheets and objects.

How to install

Prerequisites you need before installation include Python 3.12 or newer and a Qlik Sense Enterprise deployment with valid certificates for authentication.

Install using the recommended runtime for a quick start.

uvx qlik-sense-mcp-server

Configuration

The server uses environment variables to configure the connection to Qlik Sense and the MCP ports. Create a configuration file and populate the required values to establish secure access to the Repository and Engine APIs.

Key environment variables include the URL to your Qlik Sense server, user directory, user ID, and paths to client certificates. You also configure the ports for Repository, Engine, and optional HTTP metadata requests, as well as SSL verification and timeouts.

Example configuration snippet for your environment (values in angle brackets should be replaced with your actual data):

# Environment variables for Qlik Sense MCP Server
QLIK_SERVER_URL=https://your-qlik-server.company.com
QLIK_USER_DIRECTORY=COMPANY
QLIK_USER_ID=your-username

# Certificate paths (absolute paths)
QLIK_CLIENT_CERT_PATH=/path/to/certs/client.pem
QLIK_CLIENT_KEY_PATH=/path/to/certs/client_key.pem
QLIK_CA_CERT_PATH=/path/to/certs/root.pem

# API ports (standard Qlik Sense ports)
QLIK_REPOSITORY_PORT=4242
QLIK_ENGINE_PORT=4747

# Optional HTTP port for metadata requests
QLIK_HTTP_PORT=443

# SSL settings
QLIK_VERIFY_SSL=false

Usage notes and examples

You can start the MCP server via your chosen runtime and then use an MCP client to invoke tools such as get_apps, get_app_details, get_app_script, get_app_field_statistics, engine_create_hypercube, get_app_field, get_app_variables, get_app_sheets, get_app_sheet_objects, and get_app_object.

Troubleshooting

If you encounter certificate or connection issues, verify the certificate paths and that SSL verification is configured correctly. Ensure ports 4242 (Repository), 4747 (Engine), and optional HTTP metadata endpoints are reachable from your MCP client. Review user permissions in Qlik Sense and confirm that the authenticated user has access to the required APIs.

Notes

For development or local testing, you can install without affecting your system Python environment. Choose the uvx method for a quick start or install via pip if you prefer a traditional Python installation.

Available tools

get_apps

Get comprehensive list of applications with metadata via Repository API with pagination and filtering.

get_app_details

Get compact app overview including metadata, fields, master items, sheets/objects via Repository API.

get_app_sheets

Get list of sheets from an application with titles and descriptions via Engine API.

get_app_sheet_objects

Get objects from a specific sheet with IDs, types and descriptions via Engine API.

get_app_script

Extract the load script from an application via Engine API.

get_app_field

Return values of a field with pagination and wildcard search via Engine API.

get_app_variables

Return variables split by source (script/ui) with pagination and wildcard search via Engine API.

get_app_field_statistics

Get comprehensive statistics for a field via Engine API.

engine_create_hypercube

Create a hypercube for data analysis via Engine API.

get_app_object

Retrieve layout of a specific object by ID using GetObject and GetLayout via Engine API.