Zaturn (SQL Data Analysis)
Connects to multiple database types to enable SQL querying with visualization capabilities while keeping data in its original loca
Zaturn is an AI-powered data analysis MCP server that connects to various data sources (PostgreSQL, SQLite, DuckDB, MySQL, CSV, Parquet) and enables SQL querying with visualization capabilities. Developed by Karthik Devan, it keeps data in its original location while allowing AI to draft and run SQL queries, processing only the results rather than entire datasets. The server includes tools for data source management, query execution, and multiple visualization types (scatter plots, histograms, bar charts), making it ideal for business intelligence tasks and data exploration without requiring the upload of complete datasets to AI systems.
Source
Repository: https://github.com/kdqed/zaturn
Maintain Zaturn (SQL Data Analysis)?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/mcp/kdqed-zaturn?ref=badge) Related mcp
Dynoxide DynamoDB-compatible database engine in Rust on SQLite, with an MCP server for coding agents.
Sling Data integration tool for querying databases, running data pipelines, and managing replications across 30+ systems
Misata Generates realistic, multi-table synthetic datasets from natural language descriptions, YAML schemas, or existing databases with r
OneCite Generate academic citations from DOI, arXiv, titles, or URLs in BibTeX, APA, MLA formats
LibSQL Memory Provides a LibSQL-based persistent memory database for storing and retrieving knowledge graph entities and relations across conver
Metabase Integrates with Metabase business intelligence platform to provide dashboard management, query execution, database connectivity wi