DBHub is a zero-dependency, token-efficient Model Context Protocol (MCP) server that acts as a lightweight gateway. It enables MCP-compatible clients to securely connect to and manage various databases like PostgreSQL, MySQL, and SQLite through a unified interface with built-in safety controls.

dbhub

Active·★ 3.6k·MIT·Updated 2026-10-13

★ Hidden Gem★ Data Processing★ Dev Tooling

DBHub, brought to you by Bytebase, is a zero-dependency, token-efficient MCP server that acts as a lightweight gateway between MCP clients (Claude Desktop, Claude Code, Cursor, VS Code, Copilot CLI) and databases. It supports PostgreSQL, MySQL, SQL Server, MariaDB and SQLite.

It exposes a small set of MCP tools: execute_sql, which runs SQL queries with transaction support and safety controls, search_objects, which searches and explores schemas, tables, columns, indexes and procedures with progressive disclosure, and custom tools, which are reusable parameterised SQL operations you define in a dbhub.toml configuration file. A built-in web workbench lets you run queries and custom tools and view requests visually. The README includes quick-start and multi-database setup sections, and the project is MIT licensed.

#MCP Server#Database Gateway#SQL Client#Multi-Database#Zero Dependency#Developer Tools#Database Security

Features

01Zero-dependency and token-efficient design for streamlined local development.

02Supports multiple database types (PostgreSQL, MySQL, SQL Server, etc.) via a single interface.

03Connect to and manage multiple databases concurrently using TOML configuration.

04Built-in guardrails including read-only mode, row limiting, and query timeout to prevent runaway operations.

05Enhanced secure access with SSH tunneling and SSL/TLS encryption for database connections.

Why choose it

+Small tool surface (execute_sql, search_objects, custom tools) that keeps token use low.

+Supports five databases through one gateway: PostgreSQL, MySQL, SQL Server, MariaDB and SQLite.

+Custom tools let you expose only reviewed, parameterised SQL operations through dbhub.toml.

+Built-in web workbench to test queries and tools; MIT licensed.

Trade-offs

!execute_sql lets an assistant run SQL against your database, so use read-only credentials or custom tools for anything important.

!Only five database engines are supported (no MongoDB, Redis or similar).

!The README is short and defers detail to the documentation site.

Compatibility

PostgreSQL

Database

Verified via docs

MySQL

Database

Verified via docs

SQL Server

Database

Verified via docs

MariaDB

Database

Verified via docs

SQLite

Database

Verified via docs

MCP Clients

Client Integration

Verified via docs

Quick start

$ docker run --rm --init --name dbhub --publish 8080:8080 bytebase/dbhub --transport http --port 8080 --dsn "postgres://user:password@localhost:5432/dbname?sslmode=disable"

Use cases

↳Providing a unified gateway for various AI/developer clients (e.g., Claude, VS Code) to interact with diverse databases.

↳Managing multiple database environments (production, staging, development) efficiently from a single DBHub instance.

↳Safely executing SQL queries and exploring database schemas with transaction support and safety controls.

↳Defining and running custom reusable, parameterized SQL operations via configuration files.

↳Interacting with database tools and viewing request traces via a built-in web interface without requiring an MCP client.

Alternatives

GitHub MCP Server★ 33.6k

GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).

python-sdk★ 24.6k

The official Python SDK for Model Context Protocol servers and clients

Context7★ 63.0k

MCP Server that provides up-to-date code documentation for LLMs and AI code editors.

CopilotKit★ 38.0k

React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic Frontend.

pal-mcp-server★ 11.8k

The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.

E2B★ 14.3k

Open-source infrastructure for running AI-generated code in secure, isolated cloud sandboxes, with SDKs for code execution and desktop computer use.

devin.cursorrules★ 6.0k

Magic to turn Cursor/Windsurf as 90% of Devin

dbx★ 26.4k

20 MB lightweight cross-platform database client for 70+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具，支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 70+ 数据库，提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。

See all alternatives →

Featured in these lists

Best MCP Servers for Databases

Comments

No comments yet. Be the first!

dbhub

Active·★ 3.6k·MIT·Updated 2026-10-13

★ Hidden Gem★ Data Processing★ Dev Tooling

#MCP Server#Database Gateway#SQL Client#Multi-Database#Zero Dependency#Developer Tools#Database Security

Features

01Zero-dependency and token-efficient design for streamlined local development.

02Supports multiple database types (PostgreSQL, MySQL, SQL Server, etc.) via a single interface.

03Connect to and manage multiple databases concurrently using TOML configuration.

04Built-in guardrails including read-only mode, row limiting, and query timeout to prevent runaway operations.

05Enhanced secure access with SSH tunneling and SSL/TLS encryption for database connections.

Why choose it

+Small tool surface (execute_sql, search_objects, custom tools) that keeps token use low.

+Supports five databases through one gateway: PostgreSQL, MySQL, SQL Server, MariaDB and SQLite.

+Custom tools let you expose only reviewed, parameterised SQL operations through dbhub.toml.

+Built-in web workbench to test queries and tools; MIT licensed.

Trade-offs

!execute_sql lets an assistant run SQL against your database, so use read-only credentials or custom tools for anything important.

!Only five database engines are supported (no MongoDB, Redis or similar).

!The README is short and defers detail to the documentation site.

Compatibility

PostgreSQL

Database

Verified via docs

MySQL

Database

Verified via docs

SQL Server

Database

Verified via docs

MariaDB

Database

Verified via docs

SQLite

Database

Verified via docs

MCP Clients

Client Integration

Verified via docs

Quick start

$ docker run --rm --init --name dbhub --publish 8080:8080 bytebase/dbhub --transport http --port 8080 --dsn "postgres://user:password@localhost:5432/dbname?sslmode=disable"

Use cases

↳Providing a unified gateway for various AI/developer clients (e.g., Claude, VS Code) to interact with diverse databases.

↳Managing multiple database environments (production, staging, development) efficiently from a single DBHub instance.

↳Safely executing SQL queries and exploring database schemas with transaction support and safety controls.

↳Defining and running custom reusable, parameterized SQL operations via configuration files.

↳Interacting with database tools and viewing request traces via a built-in web interface without requiring an MCP client.

Alternatives

GitHub MCP Server★ 33.6k

GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).

python-sdk★ 24.6k

The official Python SDK for Model Context Protocol servers and clients

Context7★ 63.0k

MCP Server that provides up-to-date code documentation for LLMs and AI code editors.

CopilotKit★ 38.0k

React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic Frontend.

pal-mcp-server★ 11.8k

The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.

E2B★ 14.3k

Open-source infrastructure for running AI-generated code in secure, isolated cloud sandboxes, with SDKs for code execution and desktop computer use.

devin.cursorrules★ 6.0k

Magic to turn Cursor/Windsurf as 90% of Devin