TabularisDB/tabularis

Open-source desktop SQL workspace for PostgreSQL, MySQL/MariaDB, SQLite and 15+ more databases like DuckDB, ClickHouse, Redis and Firestore. Built-in MCP server for Claude, Cursor and Devin, SQL notebooks and visual EXPLAIN.

What it solves

Tabularis is a desktop SQL workspace designed to simplify database management across multiple platforms. It solves the problem of needing different tools for different databases by providing a unified interface for PostgreSQL, MySQL/MariaDB, SQLite, and over 15 other databases via a plugin system.

How it works

Built with React and Rust (Tauri), the application provides a comprehensive suite of tools for interacting with databases. It uses a plugin architecture where drivers are standalone executables communicating via JSON-RPC, allowing support for any database. It also integrates AI capabilities through various providers (including local models via Ollama) and implements the Model Context Protocol (MCP) to allow AI agents like Claude and Cursor to interact with the user's database schema and run queries.

Who it’s for

It is intended for developers, data analysts, and database administrators who need a versatile, open-source SQL client with advanced features like notebooks and AI integration.

Highlights

  • AI-Powered Workflow: Includes text-to-SQL and query explanation using OpenAI, Anthropic, and local Ollama models.
  • MCP Server Integration: A built-in MCP server allows AI agents to read schemas and execute queries directly.
  • SQL Notebooks: A multi-cell workspace combining SQL and Markdown with cross-cell variables and built-in charting.
  • Extensible Plugin System: Support for additional databases can be added using plugins written in any language.
  • Visual Tools: Features a visual query builder and interactive Visual EXPLAIN plan graphs for query optimization.
  • Broad Database Support: Native support for PostgreSQL, MySQL, and SQLite, with plugins for DuckDB, ClickHouse, Redis, and more.

Related

  • Project
    FreePeak/db-mcp-server

    A multi-database server implementing the Model Context Protocol (MCP) that provides AI assistants with structured and secure access to multiple database engines.

  • Project
    bytebase/dbhub

    A minimal, token-efficient MCP server that enables AI agents to securely connect to, explore, and query multiple database types through a single interface.

  • Project
    googleapis/mcp-toolbox

    An open-source MCP server that connects AI agents and IDEs to enterprise databases via prebuilt generic tools or a custom framework for secure, structured data access.

  • Project
    Klavis-AI/klavis

    Klavis is a platform for AI agents to access hundreds of prebuilt MCP-based tool integrations, featuring intelligent connectors to optimize context window usage and sandboxes for LLM training.

  • Project
    dbt-labs/dbt-mcp

    An MCP server that provides AI agents with tools to interact with dbt Core, Fusion, and Platform, enabling them to query data, manage lineage, and execute dbt workflows.