Zero-dependency, token-efficient MCP server for querying multiple databases via a single interface.
dbhub is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view bytebase/dbhub --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
DBHub is a lightweight tool that lets AI coding assistants like Claude or Cursor connect to databases. It supports PostgreSQL, MySQL, SQL Server, MariaDB, and SQLite. You can run SQL queries and explore database schemas without installing heavy dependencies.
DBHub is a Model Context Protocol (MCP) server that provides a unified gateway for MCP-compatible AI agents to interact with multiple database systems. It is designed to be minimal and token-efficient, exposing only two core MCP tools (execute_sql and search_objects) to maximize the context window for AI interactions. DBHub supports PostgreSQL, MySQL, MariaDB, SQL Server, and SQLite, and allows simultaneous connections to multiple databases via a TOML configuration file. It includes safety features such as read-only mode, row limiting, and query timeout to prevent runaway operations. Additionally, it supports SSH tunneling and SSL/TLS encryption for secure access. DBHub can be run via Docker or npm, and includes a built-in web workbench for visual database interaction.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 97 days ago.
2858 GitHub stars indicate community interest.
13 open issues signal maintenance load.
MIT license detected.
Let an AI coding assistant query a PostgreSQL database to generate reports or debug issues.
Explore database schemas across multiple MySQL and SQLite databases from a single MCP client.
Run safe
read-only SQL queries on a production SQL Server database with row limits and timeouts.
Connect Claude Desktop to a MariaDB database for natural language data analysis.
Use DBHub's custom tools to define reusable parameterized SQL operations for common tasks.
Running in read-write mode could allow AI agents to modify or delete data; use read-only mode for production.
Exposing the server without authentication may lead to unauthorized database access.
SQL injection is possible if the AI agent generates malicious queries; use parameterized queries and row limits.
2,858
Stars
239
Forks
13
Issues
MIT
License
Official MCP reference servers from Anthropic. Includes servers for filesystem, GitHub, Postgres, Slack, and more.
A secure MCP server for AI applications to interact with MySQL databases.
Up-to-date code documentation for LLMs and AI code editors, eliminating outdated or hallucinated API references.
Zero-dependency, token-efficient MCP server for querying multiple databases via a single interface.
AI/ML developers building agentic workflows that need database access, Full-stack developers using AI coding assistants like Claude or Cursor, Database administrators who want to integrate AI tools with their databases
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Running in read-write mode could allow AI agents to modify or delete data; use read-only mode for production. Exposing the server without authentication may lead to unauthorized database access.
Similar or complementary options to evaluate include MCP Server Collection, mysql_mcp_server, context7.
Jun 2, 2026
3 security/trust notes recorded.
Setup difficulty is 2/5.