qlik

The Qlik MCP Server provides comprehensive access to Qlik Sense applications via the MCP protocol. It exposes 9 tools that allow you to list apps, fetch measures, variables, fields, sheets, sheet objects, dimensions, and the script and data sources for each app. It also supports certificate-based authentication over a direct WebSocket connection to a Qlik Sense Enterprise environment, enabling secure and production-ready interactions with AI assistants and other MCP clients. With these capabilities, you can generate documentation, perform migration analysis, validate governance controls, and automate QA workflows by querying for detailed app structures and metadata.

To use the server, start it using the Python module entry point described in the Quick Start section of the README. Once running, you can invoke the 9 tools through MCP clients like Claude Desktop, Cursor IDE, or other MCP-compatible consumers. For example, you can request list_qlik_applications to obtain a catalog of apps with metadata, or get_app_script to retrieve and analyze loading scripts along with Binary Load statements. Enhanced script analysis supports section parsing, line counts, and source references, making it easier to document and audit complex Qlik Sense apps.

Prerequisites:

• Python 3.10+ (recommended by the project)
• UV package manager recommended for dependency handling (optional but suggested)
• Access to a Qlik Sense Enterprise server
• Valid Qlik client certificates (certificate setup described in docs/CERTIFICATES.md)

Installation steps:

1. Clone the repository git clone https://github.com/arthurfantaci/qlik-mcp-server.git cd qlik-mcp-server

2. Install dependencies using UV (recommended) or standard Python tooling curl -LsSf https://astral.sh/uv/install.sh | sh # Install UV if not already installed uv sync # Creates virtual environment and installs dependencies (Alternatively) python -m pip install -r requirements.txt

3. Prepare environment and configuration

   • Copy example environment file cp .env.example .env
   • Edit .env with your Qlik Sense server details and certificate paths

4. Start the server

   • Run the module as the MCP server (example): /path/to/python3 -m src.server

5. Verify installation

   • Connect with an MCP client and validate the available tools (list_qlik_applications, get_app_measures, etc.).

Tips and common issues:

• Ensure Qlik Sense Enterprise is accessible from the host running the MCP server and that certificate-based authentication is correctly configured.
• If you encounter module import errors, re-create the virtual environment using UV or install dependencies with your preferred Python tool.
• The environment variable placeholders in mcp_config can be filled with real values or kept as placeholders for documentation purposes.
• For Cursor IDE or Claude Desktop integrations, follow the configuration steps in the README's Quick Start to point at the running MCP server and certificates.
• The 9 tools cover a broad set of Qlik Sense metadata; ensure your Qlik Sense permissions align with the data you intend to access to avoid authorization errors.
• When testing integration, start with unit tests before attempting full integration tests, especially if a Qlik server is not always available.