Dashboard Generator · cwtwb

Describe your dashboard. Get a Tableau file.

cwtwb generates production-ready .twb and .twbx files from natural language. A guided step-by-step process confirms data source, chart layout, and style before delivery.

Get Started - 2 min GitHub

cwtwb Tableau workbook automation preview

Quick Start

Install the package, configure MCP, then describe what you need. pip install cwtwb

# MCP Server Config Example
{
  "mcpServers": {
    "cwtwb": {
      "command": "uvx",
      "args": ["cwtwb"]
    }
  }
}

# Prompt Example
"Boot a guided authoring process linked to local sales.hyper;"
"Assemble a synchronized dual-axis line chart involving [Sales] and [Profit];"

Core Capabilities

Guided Authoring

Guided step-by-step

Walk through data, layout, charts, and style. Each step is confirmed before moving on.

Safe Migration

Edit existing workbooks

Open, modify, and re-save .twbx files including their embedded data.

Chart Recipes

Complex charts, one instruction

Built-in recipes for dual-axis, butterfly, Sankey, and more.

Validation

Files that open

Every file is checked against Tableau format expectations before delivery.

Capability Matrix

Feature	Datacooper	Default workflow	Advantage
Output	Complete .twb/.twbx files	Temporary chart screenshots	Generate files that can be opened, shared, published, or version-controlled.
Layout control	Full control	Fixed auto-layout	Match exact client requirements for sizing, colors, and positioning.
Automation	API + CLI	UI only	Generate dashboards from scripts and integrate with existing pipelines.

FAQ

Do I need to know Tableau to use cwtwb?

No. You describe what you want in plain language and cwtwb handles the Tableau-specific file structure. Knowing basic Tableau concepts still helps you write better prompts.

How is this different from asking ChatGPT to write a TWB file directly?

Generic LLM output often produces XML that looks plausible but fails in Tableau. cwtwb uses a purpose-built engine and validates files before delivery.

Which AI models are supported?

Any model that supports MCP tool calls can work, including Claude, ChatGPT through an MCP bridge, Gemini, and DeepSeek.

Can I use my company brand colors?

Yes. You can define brand colors and styling once in your recipe or prompt conventions, and cwtwb applies them consistently.

Core features open source. Advanced features and deployment on request.