What databases does Dbhub support?
PostgreSQL, MySQL, MariaDB, SQL Server, and SQLite.
@bytebase
基本信息
Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"dbhub": {
"command": "docker",
"args": [
"run",
"--rm",
"--init",
"\\"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Dbhub is a zero-dependency, token-efficient MCP (Model Context Protocol) server that allows MCP-compatible clients to connect to and explore various databases. It supports PostgreSQL, MySQL, MariaDB, SQL Server, and SQLite through a single interface and is brought to you by Bytebase.
Install via Docker or NPM, then start with command-line arguments such as --transport, --port, and --dsn. For multi-database setups, use a TOML configuration file. Demo mode is available via --demo. The server also includes a built-in web interface (Workbench) for visual interaction.
PostgreSQL, MySQL, MariaDB, SQL Server, and SQLite.
Use Docker (`docker run --rm --init --name dbhub --publish 8080:8080 bytebase/dbhub`) or NPM (`npx @bytebase/dbhub@latest`) with required flags like `--transport`, `--port`, and `--dsn`. A demo mode is also available.
The HTTP transport does not authenticate HTTP clients. For production, bind to `127.0.0.1` and use a reverse proxy or firewall.
Read-only mode, row limiting, and query timeout to prevent runaway operations.
Yes, Dbhub includes a built-in Workbench that provides a visual way to execute queries, run custom tools, and view request traces without needing an MCP client.

Oracle MCP server with no run-sql tool: It generates tools for each of the PL/SQL procedures, tables and approved SQL you choose. The server doesn't expose a SQL prompt, and can't reveal how it's connected to Oracle.
A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters.
MCP server for interacting with Neon Management API and databases
An official Qdrant Model Context Protocol (MCP) server implementation
Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.
评论