Qlik Sense MCP Server
The Qlik Sense MCP Server provides a unified interface for interacting with Qlik Sense Enterprise APIs, enabling comprehensive application management, data analysis, and administrative operations.
Core Capabilities:
Application Management: Retrieve application lists with filtering and pagination (
get_apps), detailed metadata including object counts (get_app_details,get_app_metadata), and load scripts (engine_get_script)Data Analysis & Extraction: Extract field values with frequency (
engine_get_field_values), generate statistical analysis including min/max/median/standard deviation (engine_get_field_statistics), create hypercubes for advanced analysis (engine_create_hypercube), and export data in JSON/CSV formats (engine_create_data_export)Administrative Management: Access users (
get_users), streams (get_streams), data connections (get_data_connections), tasks (get_tasks), extensions (get_extensions), and content libraries (get_content_libraries)Task Automation: Execute specific tasks by ID (
start_task) for automated workflowsEngine API Integration: Direct interaction with Qlik Sense Engine API for document listing (
engine_get_doc_list), application operations, sheet retrieval (engine_get_sheets), and table data extraction (engine_get_table_data)Security & Performance: Certificate-based authentication for secure access, optimized queries, and pagination for efficient data retrieval
Uses .ENV files for configuration management of Qlik Sense connection details, authentication credentials, and API settings.
Integrates with GitHub Actions for automated build and publication processes to PyPI when new version tags are pushed.
Supports installation from PyPI and automated publication of new versions through GitHub Actions workflows.
Provides unified interface for Qlik Sense Enterprise Repository API and Engine API operations, enabling access to applications, users, data models, analytics, and data export functionality through 21 specialized tools.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Qlik Sense MCP Serverlist all applications with their metadata"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Qlik Sense MCP Server
Model Context Protocol server for Qlik Sense Enterprise. Exposes Qlik's Repository (HTTP) and Engine (WebSocket) APIs as 24 MCP tools so an LLM client can discover apps, inspect data models, build hypercubes, and manage reload tasks through a single uniform interface.
What's in the box
Area | Tools | Used for |
Repository (apps & metadata) |
| Discover apps, list tables and fields with cardinalities |
Engine (data & script) |
| Read load script, list visualizations, query field values, build hypercubes |
Reload tasks |
| Inspect, trigger and manage reload tasks |
Full list with descriptions: docs/tools.md.
Related MCP server: Opik MCP Server
Quick start
uvx qlik-sense-mcp-serverThe server starts in Streamable HTTP
mode on http://127.0.0.1:8000/mcp. Configure it via environment
variables — see docs/configuration.md.
For stdio mode (legacy MCP transport), pass --stdio.
Documentation
Document | What's inside |
Requirements, install via | |
All | |
Transports, server start commands, recommended call order, hard limits enforced by this server | |
Inventory of all 24 tools, response/error envelope, error categories | |
Project layout, components, connection caching, strict id-matching, two-tier timeout | |
| |
Common errors, hypercube planning failures, verbose logging, configuration self-test | |
Release notes |
Key facts about the v1.4.0 line
Cached Engine WebSocket connections. Once an app is opened, every subsequent tool call against the same
app_idreuses the same WebSocket and the same open document. Switchingapp_idcloses the old document and opens the new one on the same socket. Dropped connections are reopened transparently. Implementation:engine_api.pyanddocs/architecture.md.Streamable HTTP transport by default. The server is a long-lived process; multiple MCP clients can talk to it in parallel. The legacy stdio mode still works behind
--stdio.tool_call_secondsis injected as the first key of every tool response — wall-clock time of the call in milliseconds. Use it to spot slow tools.Hard hypercube limits.
engine_create_hypercuberejects requests withmax_rows > 5000orcolumns * max_rows > 9900immediately, with a structured error and a hint pointing at set-analysis or top-N patterns. Qlik Engine itself returns error 7009calc-pages-too-largefor any single page over 10000 cells.Single timeout knob.
QLIK_WS_TIMEOUT(default180.0seconds) controls both the WebSocket handshake and every Engine API call.
Requirements
Python 3.12 (the package is built and tested against this version; see
pyproject.toml)Qlik Sense Enterprise (Repository on port 4242, Engine on port 4747 — the standard ports)
Client certificate, private key and root CA from the Qlik Sense node
Network access from the host running this server to Qlik
Disclaimer
This project is an independent, community-built integration. It is NOT affiliated with, endorsed by, sponsored by, or supported by Qlik Technologies Inc., QlikTech International AB, or any other Qlik entity. "Qlik", "Qlik Sense", "QlikView" and all related product names are trademarks of their respective owners.
All information about Qlik Sense APIs, port allocations, error codes, protocol behavior and usage patterns used in this project was obtained exclusively from publicly available sources — the Qlik Developer Portal (help.qlik.com, qlik.dev), the Qlik Community forums, and other public documentation. No proprietary, confidential or reverse-engineered material is used.
License
MIT © 2025-2026 Stanislav Chernov
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/bintocher/qlik-sense-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server