MariaDB / MySQL Database Access MCP Server

@rjsalgado

代码仓库

基本信息

分类

数据库

许可证

MIT

传输方式

stdio

作者

rjsalgado

关于 MariaDB / MySQL Database Access MCP Server

An MCP server that provides access to MariaDB ou MySQL databases.

MariaDB / MySQL Database Access MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mariadb": {
      "command": "npx",
      "args": [
        "mariadb-mcp-server"
      ],
      "env": {
        "MARIADB_HOST": "",
        "MARIADB_PORT": "",
        "MARIADB_USER": "",
        "MARIADB_PASSWORD": "",
        "MARIADB_DATABASE": "",
        "MARIADB_ALLOW_INSERT": "",
        "MARIADB_ALLOW_UPDATE": "",
        "MARIADB_ALLOW_DELETE": "",
        "MARIADB_TIMEOUT_MS": "",
        "MARIADB_ROW_LIMIT": ""
      }
    }
  }
}

MariaDB / MySQL Database Access MCP Server 工具

List all accessible databases on the MariaDB server

List all tables in a specified database

Show the schema for a specific table

Execute a SQL query

概览

What is MariaDB / MySQL Database Access MCP Server?

This MCP server provides read-only access to MariaDB or MySQL databases, enabling listing of databases, tables, table schemas, and execution of SQL queries through the Model Context Protocol. It is intended for developers and data analysts who need safe, structured database exploration via AI tools.

How to use MariaDB / MySQL Database Access MCP Server?

Install the server globally or locally via npm (npm install -g mariadb-mcp-server) or build from source. Configure environment variables such as MARIADB_HOST, MARIADB_USER, MARIADB_PASSWORD, etc. Add a server entry to your MCP settings JSON with the command npx mariadb-mcp-server and the required environment variables. The server exposes four tools: list_databases, list_tables, describe_table, and execute_query.

Key features of MariaDB / MySQL Database Access MCP Server

Read-only access by default (SELECT, SHOW, DESCRIBE, EXPLAIN)
SQL injection prevention through query validation
Query timeout to prevent resource exhaustion
Configurable row limit to cap returned data

Use cases of MariaDB / MySQL Database Access MCP Server

Enumerate databases and tables for data discovery
Inspect table schemas without direct SQL client access
Execute safe, read-only queries through AI assistants
Validate data structure during development or analysis

常见问题

What security features does the server have?

The server enforces read-only access by default, validates queries to prevent SQL injection, applies a configurable query timeout (default 10,000 ms), and limits rows returned (default 1000).

Which environment variables are required?

You must set `MARIADB_HOST`, `MARIADB_USER`, and `MARIADB_PASSWORD`. `MARIADB_PORT` defaults to 3306, and `MARIADB_DATABASE` is optional. Security variables like `MARIADB_ALLOW_INSERT` should be set to `false` for read-only mode.

How do I install the server?

Install via npm globally or locally: `npm install -g mariadb-mcp-server`. Alternatively, clone the repository and run `npm install && npm run build` to build from source.

Can I modify data (INSERT, UPDATE, DELETE) through this server?

No. The server is designed for read-only access. Even if you set the environment variables `MARIADB_ALLOW_INSERT`, `MARIADB_ALLOW_UPDATE`, or `MARIADB_ALLOW_DELETE` to `true`, the README instructs setting them to `false` and includes query validation that blocks data modification.

What tools does the server provide?

It provides `list_databases`, `list_tables` (optional database), `describe_table` (requires table name), and `execute_query` (requires query, optional database). All tools are read-only.

数据库分类下的更多 MCP 服务器

Lawstronaut

Lawstronaut-FZCO

Access millions of official legal and regulatory source documents from 155+ jurisdictions via MCP. Lawstronaut supports AI agents with structured legal research, legal data, laws, regulations, cases, guidance, official s

nuzur

nuzur is a model-first database platform for MySQL and PostgreSQL. The MCP server lets any AI assistant or agent (Claude, Cursor, Gemini, or anything else that speaks MCP) design your schema, query your data, generate mi