
Qlik MCP Server
Enables Claude to interact with Qlik Cloud applications and extract data from visualizations through the Qlik Cloud API.
README
Qlik MCP Server
MCP Server for the Qlik Cloud API, enabling Claude to interact with Qlik applications and extract data from visualizations.
Tools
qlik_get_apps
List all Qlik applications available in the workspace
- Optional inputs:
limit
(number, default: 100): Maximum number of apps to returnoffset
(string): Pagination offset for next page
- Returns: List of applications with their IDs and information
qlik_get_app_sheets
Get all sheets in a Qlik application
- Optional inputs:
app_id
(string): The ID of the Qlik application (defaults to QLIK_APP_ID env variable)
- Returns: List of sheets with their IDs, titles, and metadata
qlik_get_sheet_charts
Get all charts in a specific sheet
- Required inputs:
sheet_id
(string): The ID of the sheet to get charts from
- Optional inputs:
app_id
(string): The ID of the Qlik application (defaults to QLIK_APP_ID env variable)
- Returns: List of charts with their IDs, types, and positions
qlik_get_chart_data
Get data from a specific chart
- Required inputs:
sheet_id
(string): The ID of the sheet containing the chartchart_id
(string): The ID of the chart to get data from
- Optional inputs:
app_id
(string): The ID of the Qlik application (defaults to QLIK_APP_ID env variable)max_rows
(number, default: 10000): Maximum total rows to retrievepage_size
(number, default: 1000): Number of rows per requestinclude_metadata
(boolean, default: true): Include chart metadata in response
- Returns: Chart data with headers, rows, and optional metadata
Setup
Create a Qlik Cloud API Key:
- Log in to your Qlik Cloud tenant
- Navigate to Settings > API keys
- Create a new API key with appropriate access
- Save the API key securely
Configure Environment:
Create a .env
file with your Qlik Cloud credentials:
QLIK_API_KEY=your_api_key_here
QLIK_BASE_URL=your_tenant_url
QLIK_APP_ID=your_default_app_id
MAX_ROWS_PER_REQUEST=1000
MAX_TOTAL_ROWS=10000
REQUEST_DELAY_MS=100
MAX_RETRIES=3
RETRY_DELAY_MS=1000
Usage with Claude Desktop
Add the following to your claude_desktop_config.json
:
Using Deno (Recommended)
{
"mcpServers": {
"qlik": {
"command": "/path/to/deno",
"args": ["run", "--allow-all", "--env-file=.env", "src/index.ts"],
"cwd": "/path/to/qlik-mcp"
}
}
}
Using Node.js
{
"mcpServers": {
"qlik": {
"command": "npx",
"args": ["tsx", "src/index.ts"],
"env": {
"QLIK_API_KEY": "your_api_key_here",
"QLIK_BASE_URL": "your_tenant_url",
"QLIK_APP_ID": "your_default_app_id"
},
"cwd": "/path/to/qlik-mcp"
}
}
}
Usage with Cursor
- Open Cursor settings
- Navigate to the Claude configuration section
- Add a new MCP configuration:
{
"name": "Qlik Cloud",
"command": "/path/to/deno",
"args": ["run", "--allow-all", "--env-file=.env", "src/index.ts"],
"cwd": "/path/to/qlik-mcp"
}
Replace /path/to/deno
with your Deno installation path (usually ~/.deno/bin/deno
on Unix systems) and /path/to/qlik-mcp
with the absolute path to your cloned repository.
Troubleshooting
If you encounter errors, verify that:
- Your API key has the necessary permissions
- The tenant URL is correct and accessible
- The app ID exists and is accessible
- Environment variables are properly set
- Rate limiting settings are appropriate for your tenant
Common issues:
401 Unauthorized
: Check your API key403 Forbidden
: Verify API key permissions429 Too Many Requests
: Adjust rate limiting settings404 Not Found
: Verify app and sheet IDs
Development
Prerequisites
Local Setup
# Clone repository
git clone https://github.com/jwaxman19/qlik-mcp.git
cd qlik-mcp
# Install dependencies (for IDE support)
npm install
# Run server
deno task dev
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.