Generating Tableau Prep data flow (.tfl) files
cwprep - Text-to-PrepFlow Engine
cwprep is a Python-based engine that enables Text-to-PrepFlow generation.
By reverse-engineering the .tfl JSON structure and providing a built-in MCP (Model Context Protocol) server, cwprep acts as a bridge between LLMs (like Claude, Gemini) and Tableau Prep. You can now generate, modify, and build data cleaning flows simply through natural language conversations or Python scripts, without ever opening the GUI!
Installation
pip install cwprep
Quick Start
from cwprep import TFLBuilder, TFLPackager
# Create builder
builder = TFLBuilder(flow_name="My Flow")
# Add database connection
conn_id = builder.add_connection(
host="localhost",
username="root",
dbname="mydb"
)
# Add input tables
orders = builder.add_input_table("orders", "orders", conn_id)
customers = builder.add_input_table("customers", "customers", conn_id)
# Join tables
joined = builder.add_join(
name="Orders + Customers",
left_id=orders,
right_id=customers,
left_col="customer_id",
right_col="customer_id",
join_type="left"
)
# Add output
builder.add_output_server("Output", joined, "My_Datasource")
# Build and save
flow, display, meta = builder.build()
TFLPackager.save_tfl("./my_flow.tfl", flow, display, meta)
By default, both the SDK and MCP output only the final .tfl/.tflx archive. Use save_to_folder() only when you explicitly want the exploded folder for inspection.
Features
| Feature | Method | Description |
|---|---|---|
| Database Connection | add_connection() |
Connect to MySQL/PostgreSQL/SQL Server |
| File Connection | add_file_connection() |
Connect to Excel (.xlsx/.xls) or CSV files |
| SQL Input | add_input_sql() |
Custom SQL query input |
| Table Input | add_input_table() |
Direct table connection |
| Excel Input | add_input_excel() |
Read from Excel worksheet |
| CSV Input | add_input_csv() |
Read from CSV file |
| CSV Union | add_input_csv_union() |
Merge multiple CSV files |
| Join | add_join() |
left/right/inner/full joins (single or multi-column) |
| Union | add_union() |
Merge multiple tables |
| Filter | add_filter() |
Expression-based filter |
| Value Filter | add_value_filter() |
Keep/exclude by values |
| Keep Only | add_keep_only() |
Select columns |
| Remove Columns | add_remove_columns() |
Drop columns |
| Rename | add_rename() |
Rename columns |
| Calculation | add_calculation() |
Tableau formula fields |
| Quick Calc | add_quick_calc() |
Quick clean (lowercase/uppercase/trim/remove) |
| Change Type | add_change_type() |
Change column data types |
| Duplicate Column | add_duplicate_column() |
Duplicate (copy) a column |
| Aggregate | add_aggregate() |
GROUP BY with SUM/AVG/COUNT |
| Pivot | add_pivot() |
Rows to columns |
| Unpivot | add_unpivot() |
Columns to rows |
| Output | add_output_server() |
Publish to Tableau Server |
| TFLX Packaging | build(is_packaged=True) |
Generate .tflx with embedded data files |
| SQL Translation | SQLTranslator |
Translate TFL flows to equivalent ANSI SQL |
Examples
See the examples/ directory for complete demos:
demo_basic.py- Input, Join, Outputdemo_cleaning.py- Filter, Calculate, Renamedemo_field_operations.py- Quick Calc, Change Type, Duplicate Columndemo_aggregation.py- Union, Aggregate, Pivotdemo_comprehensive.py- All features combinedprompts.md- 8 ready-to-use MCP prompt templates for AI-driven flow generation
MCP Server
cwprep includes a built-in Model Context Protocol server, enabling AI clients (Claude Desktop, Cursor, Gemini CLI, etc.) to generate TFL files directly.
Prerequisites
| Method | Requirement |
|---|---|
uvx (recommended) |
Install uv — it auto-downloads cwprep[mcp] in an isolated env |
pip install |
Python ≥ 3.8 + pip install cwprep[mcp] |
Quick Start
# Local (stdio)
cwprep-mcp
# Remote (Streamable HTTP)
cwprep-mcp --transport streamable-http --port 8000
[!TIP] Upgrading? If you previously used
uvxwith an older version, clear the cache to pick up the latest release:uv cache clean cwprep
Client Configuration
All clients below use the uvx method (recommended). Replace uvx with cwprep-mcp if you prefer a local pip install.
Claude Desktop
Edit config file:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"cwprep": {
"command": "uvx",
"args": ["--from", "cwprep[mcp]", "cwprep-mcp"]
}
}
}
Cursor
Settings → MCP → Add new MCP server, or edit ~/.cursor/mcp.json:
{
"mcpServers": {
"cwpre
Configuration
{"mcpServers": {"cwprep": {"command": "uvx", "args": ["--from", "cwprep[mcp]", "cwprep-mcp"]}}}