Skip to main content
Glama
undsoul

Qlik MCP Server

by undsoul

qlik_generate_app

Create or update Qlik Sense applications with load scripts and data connections for analytics workflows.

Instructions

Create or update a Qlik Sense app with load script and data connections.

Cloud workflow:

  1. qlik_get_dataset_details → get connection info

  2. qlik_generate_app with script

On-Premise workflow (Engine API):

  1. Create app via Global.CreateApp

  2. Optionally create data connection via Doc.CreateConnection

  3. Set script via Doc.SetScript

  4. Reload via Doc.DoReload

  5. Save via Doc.DoSave

On-Premise Data Connections:

  • Folder: { "connectionName": "MyData", "connectionType": "folder", "connectionString": "C:\Data\" }

  • ODBC: { "connectionName": "SQLServer", "connectionType": "ODBC", "connectionString": "DSN=MyDSN" }

On-Premise Discovery (no appName/appId needed):

  • listOdbcDsns: true → List available ODBC data sources on server

  • listConnections: true + appId → List connections in existing app

Cloud Load Script - File from Space: IMPORTANT: Use format [lib://:DataFiles/]

  • Example: FROM [lib://BI TEAM WORKSPACE:DataFiles/sales.csv] (txt, codepage is 1252, embedded labels, delimiter is ',', msq);

  • Example: FROM [lib://Finance Team:DataFiles/report.qvd] (qvd);

  • WRONG format: FROM [lib://DataFiles (spaceId)/file.csv] ← Do NOT use this!

On-Premise Load Script Examples:

  • Folder: LOAD * FROM [lib://MyData/sales.csv] (txt, codepage is 1252, embedded labels, delimiter is ',', msq);

  • ODBC: LIB CONNECT TO 'MyODBC'; SQL SELECT * FROM Sales;

Returns: appId, appName, appLink, reloadStatus, connections, odbcDsns

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
appNameNoName for new app (creates in personal space)
appIdNoExisting app ID (updates the app)
loadScriptNoQlik load script
dataConnectionNoOn-Premise only: Create a data connection before loading
listConnectionsNoOn-Premise only: List existing connections in the app (requires appId)
listOdbcDsnsNoOn-Premise only: List available ODBC data sources on the server
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure and excels. It details operational workflows, platform-specific behaviors (Cloud vs. On-Premise), data connection formats, discovery options (listOdbcDsns, listConnections), and return values (appId, appName, etc.). It also warns about incorrect script formats, adding crucial context beyond basic functionality.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (workflows, examples, returns) but is lengthy due to extensive examples and platform details. While every sentence adds value (e.g., script format warnings, connection examples), it could be more front-loaded; the core purpose is clear early, but the depth may overwhelm. It balances detail with clarity but isn't maximally concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (6 parameters, nested objects, no output schema), the description is highly complete. It covers all necessary context: purpose, usage workflows, parameter semantics, behavioral details, and return values. It compensates for the lack of annotations and output schema by providing comprehensive guidance, making it sufficient for an agent to use the tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, so the baseline is 3. The description adds significant value by explaining parameter usage in context: it clarifies when appName vs. appId is used (create vs. update), provides examples for dataConnection objects, and details how listConnections and listOdbcDsns work in On-Premise scenarios. However, it doesn't fully elaborate on all parameter interactions beyond what the schema implies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as 'Create or update a Qlik Sense app with load script and data connections,' specifying both the verb (create/update) and resource (Qlik Sense app). It distinguishes itself from sibling tools like qlik_get_dataset_details or qlik_trigger_app_reload by focusing on app generation with scripts and connections, not data retrieval or reload triggering.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidelines with detailed workflows for Cloud and On-Premise scenarios, including step-by-step sequences (e.g., 'Cloud workflow: 1. qlik_get_dataset_details → get connection info 2. qlik_generate_app with script'). It specifies when to use certain parameters (e.g., 'On-Premise only:' for dataConnection) and includes examples of correct and incorrect formats, guiding the agent on proper invocation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

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/undsoul/qlik-claude-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server