kdqed/zaturn
Link multiple data sources (SQL, CSV, Parquet, etc.) and ask AI to analyze the data for insights and visualizations.
Add to Claude Desktop config.json
{
"mcpServers": {
"kdqed-zaturn": {
"command": "python",
"args": [
"-m",
"zaturn"
]
}
}
}Get the source and run locally
git clone https://github.com/kdqed/zaturn.git ~/.mcp/zaturn
cd ~/.mcp/zaturnAbout this MCP server
Zaturn: Your Co-Pilot For Data Analytics & Business Insights
Just Chat With Your Data! No SQL, No Python.
Zaturn provides tools that enable AI models to run SQL, so you don’t have to. It can be used as an MCP or as a web interface similar to Jupyter Notebook.
Zaturn in Action
https://github.com/user-attachments/assets/d42dc433-e5ec-4b3e-bef0-5cfc097396ab
Features:
Multiple Data Sources
Zaturn can currently connect to the following data sources:
- SQL Databases: PostgreSQL, SQLite, DuckDB, MySQL, ClickHouse, SQL Server, BigQuery
- Files: CSV, Parquet
Request data source by raising an issue
Visualizations
In addition to providing tabular and textual summaries, Zaturn can also generate the following image visualizations
- Scatter and Line Plots
- Histograms
- Strip and Box Plots
- Bar Plots
- Density Heatmap (aka. 2D Histograms)
- Polar Scatter and Line Plots
Request visualizations by raising an issue
Installation & Setup
See https://zaturn.pro/docs/install
Roadmap
- Support for more data source types & more data visualizations as per community requests
- Dashboard building: Pin queries and visuals to re-run without LLM calls.
- Multi-user capabilities
- Predictive Analytics and ML features
Help And Feedback
Support The Project
If you find Zaturn useful, please support this project by:
- Starring the project
- Sponsoring the development
- Spreading the word
Your support will enable me to dedicate more of my time to Zaturn.
Example Dataset Credits
The pokemon dataset compiled by Sarah Taha and PokéAPI has been included under the CC BY-NC-SA 4.0 license for demonstration purposes.
Featured on glama.ai
Star History
Similar MCP servers
Tools and templates to create validated and maintainable data charts and dashboards.
An MCP server to convert almost any file or web content into Markdown
Model Context Protocol (MCP) Server for Jupyter.
MCP server for the Dingo: a comprehensive data quality evaluation tool. Server Enables interaction with Dingo's rule-based and LLM-based evaluation capabilities and rules&prompts listing.
Predict anything with Chronulus AI forecasting and prediction agents.
Official MCP server enabling seamless orchestration of hyperparameter search and other optimization tasks with Optuna.