Skip to main content
Glama
Zaturn
by kdqed

Zaturn te permite analizar tus datos usando el chat de IA; sin necesidad de que escribas código SQL/Python o juegues con paneles estéticamente agradables (pero abrumadores).

Puedes añadir Zaturn MCP a Claude Desktop (o a cualquier cliente MCP), conectar tus fuentes de datos, formular preguntas en lenguaje natural y obtener información instantánea con visualizaciones. Con Zaturn, tu IA puede comprender automáticamente el tipo de datos que tienes, consultarlos y ofrecerte consejos útiles con una narrativa coherente. Puedes hacer preguntas específicas como "¿Quién es nuestro cliente más valioso?" o dejar que la IA explore tus datos con una pregunta como "Aquí tienes todos los datos que tenemos; danos algunas ideas para el próximo trimestre".

Descargas de PyPI

Únete a Discord

Pero puedo simplemente cargar mis datos en ChatGPT y pedirle que los analice, ¿verdad?

Sí, pero ChatGPT tiene un límite de tamaño de carga de aproximadamente 50 MB para archivos CSV/hojas de cálculo, y la carga también lleva tiempo. Además, no puede leer datos directamente desde su servidor MySQL o PostgreSQL. Zaturn puede superar todas estas limitaciones sin mover sus datos a ningún sitio. Simplemente equipa su IA con capacidades de SQL y visualización para que pueda consultar sus datos directamente, obtener los resultados, procesarlos y brindarle información instantánea. Con Zaturn, la IA no necesita procesar su conjunto de datos completo ni almacenarlo en su memoria para responder a sus preguntas sobre los datos.

Related MCP server: Superset MCP Server

Zaturn en acción

https://github.com/user-attachments/assets/d42dc433-e5ec-4b3e-bef0-5cfc097396ab

Características:

Múltiples fuentes de datos

Actualmente Zaturn puede conectarse a las siguientes fuentes de datos:

  • Bases de datos SQL: PostgreSQL, SQLite, DuckDB, MySQL, ClickHouse

  • Archivos: CSV, Parquet

Se están agregando conectores para más fuentes de datos.

Visualizaciones

Además de proporcionar resúmenes tabulares y textuales, Zaturn también puede generar las siguientes visualizaciones de imágenes

  • Gráficos de dispersión y de líneas

  • Histogramas

  • Diagramas de tiras y de cajas

  • Gráficos de barras

NOTA: Las imágenes se mostrarán solo si su cliente MCP admite la representación de imágenes (por ejemplo, Claude Desktop)

Si su cliente MCP no admite imágenes (por ejemplo, Cursor), agregue el argumento --noimg en la configuración de MCP. Los gráficos se almacenarán como archivos y se mostrará su ubicación. Puede visualizar los gráficos con su explorador de archivos.

Se están agregando más capacidades de visualización.

Instalación y configuración

  1. Instalar uv

  2. Instalar Zaturn con uv:

uv tool install zaturn
  1. Agregar a la configuración de MCP, con fuentes de datos:

"mcpServers": {
  "zaturn": {
    "command": "zaturn_mcp",
    "args": [
      "postgresql://username:password@host:port/dbname",
      "mysql+pymysql://username:password@host:3306/dbname",
      "sqlite:////full/path/to/sample_dbs/northwind.db",
      "/full/path/to/sample_dbs/titanic.parquet",
      "/full/path/to/sample_dbs/ny_aq.csv",
      "/full/path/to/sample_dbs/duckdb_sample.duckdb"
    ]
  },
}

O agregue un sources.txt al directorio de configuración de Zaturn:

postgresql://username:password@host:port/dbname
mysql+pymysql://username:password@host:3306/dbname
clickhouse://username:password@host:port/dbname
sqlite:////full/path/to/sample_dbs/northwind.db
/full/path/to/sample_dbs/titanic.parquet
/full/path/to/sample_dbs/ny_aq.csv
/full/path/to/sample_dbs/duckdb_sample.duckdb

Este archivo debe estar en ~/.config/zaturn/sources.txt en Linux/MacOS y en %APPDATA%\zaturn\sources.txt en Windows.

Si su cliente MCP no admite la representación de imágenes, agregue el argumento --noimg :

...
    "args": [
      "--noimg",
      "mysql+pymysql://username:password@host:3306/dbname",
...
  1. Configure un aviso del sistema si su LLM/IDE le permite:

You are a helpful data analysis assistant. Use only the tool provided data sources to process user inputs. Do not use external sources or your own knowledge base.
  1. Haz una pregunta y observa la magia:

User: List the top 5 customers by revenue for Northwind
AI: 
The top 5 customers by revenue for Northwind are:

1. B's Beverages with a revenue of $6,154,115.34
2. Hungry Coyote Import Store** with a revenue of $5,698,023.67
3. Rancho grande with a revenue of $5,559,110.08
4. Gourmet Lanchonetes with a revenue of $5,552,597.90
5. Ana Trujillo Emparedados y helados with a revenue of $5,534,356.6

Hoja de ruta

  • Compatibilidad con más tipos de fuentes de datos

  • Más visualizaciones de datos

  • Análisis predictivo y previsión, por ejemplo:

Based on the revenue of the last 3 months, forecast next month's revenue.
  • Generar presentaciones y archivos PDF

Manager: 
  I need a presentation to show the boss. Can you do it by EOD?
Analyst: 
  EOD?! Are you still in the 2010s? 
  I can get it done right now. Actually, you can do it right now.
  You know what? The boss can do it right now.
  • Una interfaz de cuaderno nativa

Ayuda y comentarios

Plantea un problema o únete al Discord .

Apoya el proyecto

Si encuentras útil Zaturn, apoya este proyecto de la siguiente manera:

Tu apoyo me permitirá dedicar más tiempo a Zaturn.

Ejemplo de créditos del conjunto de datos

El conjunto de datos de Pokémon compilado por Sarah Taha y PokéAPI se ha incluido bajo la licencia CC BY-NC-SA 4.0 para fines de demostración.

Historia de las estrellas

Gráfico de la historia de las estrellas

Available Tools

12 tools
bar_plotA

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.

box_plotA

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.

density_heatmapA

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.

describe_tableB

Lists columns and their types in the specified table of specified data source.

Inputs: source_id (required), table_name (required). Returns: result

histogramB

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.

line_plotC

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_data_sourcesA

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

polar_lineA

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.

polar_scatterB

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_queryA

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

scatter_plotC

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.

strip_plotB

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.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 12 tools

    Disambiguation5/5

    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.

    Naming Consistency5/5

    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.

    Tool Count5/5

    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.

    Completeness4/5

    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.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP (Model Context Protocol) server that exposes natural language to SQL functionality, allowing any MCP-compatible client to convert plain English questions into SQL queries for database interaction using AI.
      3
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server for Apache Superset that enables AI models to manage dashboards, create charts with auto-detection, and execute SQL queries programmatically. It utilizes stateless HTTP transport to ensure compatibility with integration tools like Open WebUI.
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      An MCP server that exposes relational databases (PostgreSQL/MySQL) to AI agents with natural language to SQL query support.
      19
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that enables SQL analytics on DuckDB and MotherDuck databases, allowing AI assistants and IDEs to query and analyze data.
      MIT