The Zaturn server enables AI-driven data analysis and visualization directly from multiple data sources without requiring coding or manual data uploads.
Capabilities:
List available data sources and their types
List tables/datasets within a specified data source
Run SQL queries against supported data sources (PostgreSQL, MySQL, SQLite, DuckDB, ClickHouse, CSV, Parquet)
Display results of previously executed queries in markdown table format
Generate visualizations (scatter plots, line plots, histograms, strip plots, box plots, bar plots)
Customize visualizations with parameters like x-axis, y-axis, hue, bins, legends, and orientation
Provides community support and feedback through a Discord server
Connects to DuckDB databases to run SQL queries and generate insights from the data
Hosts source code and enables issue tracking for support and feature requests
Uses Kaggle datasets (specifically Pokemon dataset) for demonstration purposes
Connects to MySQL databases to run SQL queries and analyze data for business intelligence
Connects to PostgreSQL databases to execute SQL queries and extract analytical insights
Distributes the Zaturn package through the Python Package Index for installation
Connects to SQLite databases to run SQL queries and perform data analysis
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Zaturn show me a bar chart of sales by region from last quarter"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
Related MCP server: Superset MCP Server
https://github.com/user-attachments/assets/d42dc433-e5ec-4b3e-bef0-5cfc097396ab
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
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
See https://zaturn.pro/docs/install
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
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.
The pokemon dataset compiled by Sarah Taha and PokéAPI has been included under the CC BY-NC-SA 4.0 license for demonstration purposes.
Run query against specified source and make a bar plot using result For both csv and parquet sources, use DuckDB SQL syntax Use 'CSV' as the table name in the SQL query for csv sources. Use 'PARQUET' as the table name in the SQL query for parquet sources.
This will return an image of the plot
Inputs: source_id (required), query (required), x (required), y (required), +2 more.
Run query against specified source and make a box plot using result For both csv and parquet sources, use DuckDB SQL syntax Use 'CSV' as the table name in the SQL query for csv sources. Use 'PARQUET' as the table name in the SQL query for parquet sources.
This will return an image of the plot
Inputs: source_id (required), query (required), x (required), y (required), +1 more.
Run query against specified source and make a 2d-histogram aka. Density Heatmap using result For both csv and parquet sources, use DuckDB SQL syntax Use 'CSV' as the table name in the SQL query for csv sources. Use 'PARQUET' as the table name in the SQL query for parquet sources.
This will return an image of the plot
Inputs: source_id (required), query (required), column_x (required), column_y (required), +2 more.
Lists columns and their types in the specified table of specified data source.
Inputs: source_id (required), table_name (required). Returns: result
Run query against specified source and make a histogram using result For both csv and parquet sources, use DuckDB SQL syntax Use 'CSV' as the table name in the SQL query for csv sources. Use 'PARQUET' as the table name in the SQL query for parquet sources.
This will return an image of the plot
Inputs: source_id (required), query (required), column (required), color, +1 more.
Run query against specified source and make a line plot using result For both csv and parquet sources, use DuckDB SQL syntax Use 'CSV' as the table name in the SQL query for csv sources. Use 'PARQUET' as the table name in the SQL query for parquet sources.
This will return an image of the plot
Inputs: source_id (required), query (required), x (required), y (required), +1 more.
List all available data sources. Returns a list of unique source_ids to be used for other queries. Source type is included in the source_id string. While drafting SQL queries use appropriate syntax as per source type.
Inputs: no named parameters. Returns: result
Run query against specified source and make a polar line plot using result For both csv and parquet sources, use DuckDB SQL syntax Use 'CSV' as the table name in the SQL query for csv sources. Use 'PARQUET' as the table name in the SQL query for parquet sources.
This will return an image of the plot
Inputs: source_id (required), query (required), r (required), theta (required), +1 more.
Run query against specified source and make a polar scatter plot using result For both csv and parquet sources, use DuckDB SQL syntax Use 'CSV' as the table name in the SQL query for csv sources. Use 'PARQUET' as the table name in the SQL query for parquet sources.
This will return an image of the plot
Inputs: source_id (required), query (required), r (required), theta (required), +1 more.
Run query against specified source For both csv and parquet sources, use DuckDB SQL syntax Use 'CSV' as the table name for csv sources. Use 'PARQUET' as the table name for parquet sources.
This will return a dataframe with the results.
Inputs: source_id (required), query (required). Returns: result
Run query against specified source and make a scatter plot using result For both csv and parquet sources, use DuckDB SQL syntax Use 'CSV' as the table name in the SQL query for csv sources. Use 'PARQUET' as the table name in the SQL query for parquet sources.
This will return an image of the plot
Inputs: source_id (required), query (required), x (required), y (required), +1 more.
Run query against specified source and make a strip plot using result For both csv and parquet sources, use DuckDB SQL syntax Use 'CSV' as the table name in the SQL query for csv sources. Use 'PARQUET' as the table name in the SQL query for parquet sources.
This will return an image of the plot
Inputs: source_id (required), query (required), x (required), y (required), +1 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 12 tools
Every tool has a clearly distinct purpose: 10 visualization tools each create different plot types (bar, box, scatter, etc.), 'run_query' returns raw data, 'list_data_sources' enumerates sources, and 'describe_table' provides schema information. There is no functional overlap between tools - an agent can easily select the right tool for each task.
All tools follow a consistent snake_case naming convention with clear verb_noun patterns: visualization tools use plot_type names (bar_plot, scatter_plot), while utility tools use action_object patterns (run_query, list_data_sources, describe_table). The naming is perfectly predictable and follows a single convention throughout.
12 tools is well-scoped for a data visualization and query server. The count includes comprehensive visualization coverage (10 plot types), core data operations (run_query), and metadata utilities (list_data_sources, describe_table). Each tool earns its place without redundancy or bloat.
The toolset provides excellent coverage for data exploration and visualization: query execution, schema inspection, source enumeration, and multiple plot types. Minor gaps include lack of data modification tools (update/delete) and advanced analytics functions, but these may be outside the server's intended scope as a visualization-focused tool.
MCP server for querying and analyzing data from ad platforms, analytics tools, and spreadsheets
Text-to-SQL MCP server: read-only queries on PostgreSQL, MySQL and SQL Server with your real schema
Draxlr's remote MCP server connects AI assistants to your SQL databases and dashboards. Explore schemas, run read-only queries, manage saved queries and dashboards, and export results, all with row-level security so each user sees only their own data.
