Taking on 2–3 new engagements in 2026 — EST & PST hours

See how we work →
Databases★ 3,692

Tabularis

Open-source desktop SQL workspace for PostgreSQL, MySQL/MariaDB, SQLite and 13+ more databases like DuckDB, ClickHouse, Redis and Firestore. Built-in MCP server for Claude, Cursor and Devin, SQL notebooks and visual EXPLAIN.

by TabularisDB · TabularisDB/tabularis

How to use Tabularis with Claude

Tabularis is a Model Context Protocol (MCP) server that gives Claude and other AI agents direct access to databases capabilities. Once installed, you can use it in Claude Desktop, Cursor, VS Code with GitHub Copilot, or any MCP-compatible client.

Setup

  1. Clone or install from the GitHub repository
  2. Follow the README for environment setup and credentials
  3. Add the server to your MCP client config (claude_desktop_config.json or .cursor/mcp.json)
  4. Restart your client — Tabularis will appear in the available tools list

About Tabularis

TypeScript★ 3,692 starsUpdated Jul 2026Source: github

Tabularis is an open-source MCP server in the Databases category, built in TypeScript. It connects Claude and other MCP-compatible clients to databases systems directly. Source available on GitHub.

Use cases for Databases MCP servers

  • Query and mutate production databases via natural language
  • Run schema migrations with AI-assisted validation
  • Generate and explain SQL queries from plain English
  • Debug slow queries by pulling execution plans automatically

Where Tabularis fits in an MCP workflow

Teams use Tabularis to give Claude a direct bridge into databases workflows, so routine actions happen inside the AI client instead of across separate tabs and dashboards.

Tabularis can be connected to MCP clients by following the repository setup instructions, making it useful for teams that want AI access to databases systems.

More Databases MCP servers

Built with MCP?

Altor deploys MCP servers into production for B2B engineering teams.

We connect AI agents to your live systems — ClickHouse, Linear, Stripe, GitHub — using MCP and deploy them to production in 3 weeks. Not demo.

Talk to Altor →