Lets an AI client read database schemas and run SQL queries across PostgreSQL, MySQL, SQLite and 29 plugin drivers through a built-in MCP server.
Also known as TabularisDB/tabularis
- Stars
- 5,471
- Tools
- 5
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 14, 2026
- License
- Apache-2.0
What is Tabularis MCP?
Tabularis lets an AI client read database schemas and run SQL queries across PostgreSQL, MySQL, SQLite and 29 plugin drivers through a built-in MCP server. It exposes 5 tools, such as list_connections, list_databases, list_tables.
Summary generated from the project's README
About Tabularis MCP server
Connecting AI agents to your database schemas and running SQL queries directly from your existing development environment is what Tabularis enables. This open-source desktop SQL workspace includes a built-in MCP server that allows clients like Claude, Cursor, and Devin to interact with your data. By integrating these tools, developers can automate data exploration and query execution without switching between different applications.
The server supports a wide range of data sources through three built-in drivers for PostgreSQL, MySQL, and SQLite, along with 29 additional plugin drivers. This includes specialized support for DuckDB, ClickHouse, Redis, and Firestore. Because it functions as a desktop application, it provides a local bridge between your AI assistant and your various database connections. It is designed for developers who need to manage diverse database types through a single interface while maintaining the ability for AI agents to understand their data structures.
What you can do with it
- 1Automated schema inspectionAsk an AI agent to examine your database structure to understand table relationships.
- 2Direct SQL execution via AIHave an AI client run specific queries against your databases to retrieve information.
Written from the project's README. Every use case is checked against a quote from it.
Tabularis MCP tools 5
Detected from the READMElist_connectionslist_databaseslist_tablesdescribe_tablerun_query
| list_connections | — | |
| list_databases | — | |
| list_tables | — | |
| describe_table | — | |
| run_query | — |
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packageNot checked
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubTabularis
Tabularis is an open-source desktop SQL workspace with 3 built-in database drivers and 29 shipped driver plugins, including DuckDB, ClickHouse, Redis and Firestore. Its built-in MCP server lets Claude, Cursor and Devin (formerly Windsurf) read your schema and run queries in the same app you already use.
Download
winget install Debba.Tabularis # Windows
brew install --cask tabularis # macOS
sudo snap install tabularis # Linux
Or grab an installer directly:
The app UI is available in English, Italian, Spanish, Chinese (Simplified), Chinese (Traditional), French, German, Japanese, Russian, Korean, Tagalog, Portuguese (Brazilian) and Vietnamese.
[!TIP] Discord: Join our Discord server to talk with the maintainers, share feedback, and get help from the community.
Table of Contents
- Why tabularis?
- Installation
- Updates
- Discord
- Changelog
- Features
- Tech Stack
- Development
- Roadmap
- Contributing
- Sponsors and supporters
- Origin Story
- License
Why tabularis?
| tabularis | DBeaver CE | TablePlus | Beekeeper Studio | |
|---|---|---|---|---|
| License | Apache 2.0, free | Apache 2.0, free (Pro is paid) | Commercial | GPLv3 (paid editions) |
| SQL notebooks (SQL + Markdown cells, cross-cell variables, charts) | ✅ | ❌ | ❌ | ❌ |
| Built-in MCP server for AI agents | ✅ | ❌ | ❌ | ❌ |
| Plugins in any language (JSON-RPC over stdio) | ✅ | Java/Eclipse plugins | JavaScript plugins | ❌ |
| AI text-to-SQL with local models (Ollama) | ✅ | Cloud-based AI assistant | ❌ | ❌ |
| Visual EXPLAIN with interactive plan graphs | ✅ | ✅ | ❌ | ❌ |
| Databases out of the box | 3 built-in + 29 driver plugins | 100+ | 20+ | ~10 |
[!NOTE] Comparison as of June 2026; features in other tools may have changed since. If you need dozens of drivers, use DBeaver. Tabularis focuses on doing a few databases well.
Database support
PostgreSQL, MySQL/MariaDB and SQLite ship built in. Everything else is a plugin. The built-in PostgreSQL driver is deprecated in favour of the PostgreSQL plugin, which Tabularis installs automatically. Current coverage, mirroring the driver & plugin coverage on the website:
Shipped
On the bounty board
| Status | Databases |
|---|---|
| In progress | Meilisearch |
| Coming soon | Snowflake |
| Scoped | Amazon Redshift, TiDB |
| Open | Etcd, Firebird, SQL Anywhere |
[!NOTE] Shipped drivers are installable from the plugin registry. Everything else is on the bounty board: claim one, sponsor one, or request a database.
Installation
Windows
WinGet (Recommended)
winget install Debba.Tabularis
Direct Download
Download the installer from the Releases page and run it:
tabularis_x.x.x_x64-setup.exe
Follow the on-screen instructions to complete the installation.
macOS
Homebrew (Recommended)
brew install --cask tabularis
Direct Download
Builds from v0.13.1 onward are signed and notarized by Apple, so they open without any extra steps.
The notes below only apply to older releases (before v0.13.1) downloaded directly:
- You need to allow accessibility access (Privacy & Security) to the tabularis app. If you are upgrading and already have tabularis on the allowed list, remove it manually before accessibility access can be granted to the new version.
- You may need to run
xattr -c /Applications/tabularis.appafter copying the app to the Applications directory.
Linux (Snap)
sudo snap install tabularis
sudo snap connect tabularis:password-manager-service # allow keychain access for saved credentials
[!IMPORTANT] The
password-manager-serviceinterface is not auto-connected by the Snap Store yet. Without it, saving a connection fails with aPlatform secure storage failureerror.
Linux (Flatpak)
flatpak remote-add --if-not-exists flatpark https://dl.flatpark.org/flatpark.flatpakrepo
flatpak install flatpark dev.tabularis.Tabularis
Linux (AppImage)
Download the .AppImage file from the Releases page, make it executable and run it:
chmod +x tabularis_x.x.x_amd64.AppImage
./tabularis_x.x.x_amd64.AppImage
Arch Linux (AUR)
yay -S tabularis-bin
Updates
Tabularis checks for updates automatically on startup and notifies you when a new version is available. You can also download the latest version directly from the Releases page.
Discord
Join our Discord server to talk with the maintainers, share feedback, suggest features, or get help from the community.
Changelog
Every release is documented in CHANGELOG.md.
Features
Connection Management
Full reference on tabularis.dev →
- Support for MySQL/MariaDB, PostgreSQL (with multi-schema support) and SQLite, with multi-database selection per connection.
- Save, manage, and clone connection profiles, with optional secure password storage in the system Keychain.
- SSH Tunneling with automatic readiness detection.
- Per-Connection Appearance: override the icon (Lucide, emoji, or custom image) and accent color of each saved connection.
Database Explorer
Full reference on tabularis.dev →
- Tree View: Browse tables, columns, keys, indexes, views, and stored routines, with inline editing from the sidebar.
- ER Diagram: Interactive Entity-Relationship visualization (pan, zoom, layout) with selective table diagram generation.
- Context Actions: Show data, count rows, modify schema, duplicate/delete tables.
- SQL Dump & Import: Export and restore databases with a single flow.
- Table Export & Import: Save one table, its structure and rows, as a SQL file and import it into any connection that uses the same driver, from the sidebar or the command palette.
SQL Editor
Full reference on tabularis.dev →
- Monaco Editor with syntax highlighting and auto-completion, in a tabbed interface with isolated connections per tab and resizable split view.
- Multi-Statement Execution: Run All, Run Selected, or pick individual queries. Results appear in separate tabs with independent pagination.
- Smart Query Splitting: Correctly handles stored procedures, functions, and
$$-delimited blocks. - SQL Files: Open, edit, and save
.sql,.psql, and.pgsqlfiles in editor tabs without executing them. - Saved Queries and an AI assist overlay directly in the editor.
SQL Notebooks
Full reference on tabularis.dev →
- Multi-Cell Workspace: Combine SQL and Markdown cells in a single document, with inline results and bar/line/pie charts.
- Cross-Cell Variables: Reference another cell's full result as a table with
{{cell_N}}(expanded to a CTE at run time), plus global@paramNameparameters. - Run All: Sequential execution with stop-on-error option and completion summary.
- Persistence & Export: Auto-saved as
.tabularis-notebookfiles; export as HTML, CSV, or JSON. - Outline panel, drag & drop cell reordering, and AI-generated cell names.
Keyboard Shortcuts
Full reference on tabularis.dev →
- Built-in shortcuts for navigation, editor, and data grid actions, platform-aware (
Cmdon macOS,Ctrlon Windows/Linux). - Fully customizable: Remap any non-locked shortcut from Settings → Keyboard Shortcuts; overrides persist to
keybindings.json. - Hold
Ctrl+Shiftin the sidebar to reveal numbered badges (1–9) for instant connection switching.
Visual Query Builder
Full reference on tabularis.dev →
- Drag-and-Drop: Build queries visually with ReactFlow.
- Visual JOINs: Connect tables to create relationships.
- Advanced Logic: WHERE/HAVING filters, aggregates (COUNT, SUM, AVG), sorting, and limits.
- Real-time SQL: Instant code generation.
Visual EXPLAIN
Full reference on tabularis.dev →
- Interactive Plan Graphs: Inspect execution plans as navigable node graphs instead of raw text.
- Table, Raw, and AI Views: Switch between exact node metrics, original database output, and optional AI-assisted analysis.
- Cross-Database Support: Works with PostgreSQL, MySQL/MariaDB, and SQLite using the best available
EXPLAINformat per driver. - Faster Optimization Loops: Spot expensive scans, estimate gaps, join behavior, and optimizer choices without leaving the editor.
Data Grid
Full reference on tabularis.dev →
- Inline & Batch Editing: Modify cells and commit multiple changes at once; create, delete, and multi-select rows.
- Export: Save results as CSV or JSON, or copy selected rows straight to the clipboard.
- JSON & JSONB Cells: Syntax-highlighted in the grid, with a dedicated editor window (Tree / Monaco / Raw modes).
- Spatial Data: Initial GEOMETRY support for MySQL.
Plugin System
Full reference on tabularis.dev →
Tabularis is hackable with an external plugin system. Plugins are standalone executables that communicate with the app over JSON-RPC 2.0 via stdin/stdout, and can be written in any language.
- Install Plugins: Browse and install community drivers from Settings → Available Plugins, no restart required.
- Manage Drivers: View all registered drivers (built-in and plugins) in Settings → Installed Drivers and uninstall plugins with one click.
- Any Database: Add support for DuckDB, MongoDB, or any other database by writing or installing a plugin.
- Plugin Registry: Official plugins are listed in
plugins/registry.json. - Developer Guide: See
plugins/PLUGIN_GUIDE.mdto build your own driver in any language. - Declarative themes (development): Settings → Appearance supports local packages (Import theme → Local package), previews and personal/VS Code imports without executable plugin activation. See the theme author guide for the separate
tabularis-themeCLI, packaging and release gates; public runtime/tooling rollout is not implied by this development feature.
Logging
- Real-time log viewer in Settings, with level filtering and export to
.logfiles. - Automatically expand and inspect SQL queries in logs.
- CLI Debug Mode: Start with
tabularis --debugfor verbose logging from launch.
Tabularis MCP questions
What tools does Tabularis MCP provide?
It exposes 5 tools, including list_connections, list_databases, list_tables, describe_table, run_query.
Which databases can Tabularis connect to?
PostgreSQL, MySQL/MariaDB and SQLite are built in, and 29 additional driver plugins cover databases such as DuckDB, ClickHouse, Redis, SQL Server and Firestore.
What does the built-in MCP server let AI agents do?
The built-in MCP server lets Claude, Cursor and Devin read your schema and run queries inside the Tabularis app.
Does Tabularis support AI text-to-SQL with local models?
Yes, it offers AI text-to-SQL that can run on local models via Ollama.
What is Tabularis licensed under?
Tabularis is free and open source under the Apache 2.0 license.
Does Tabularis have SQL notebooks?
Yes, it supports SQL notebooks with SQL and Markdown cells, cross-cell variables and charts.