MCP-MySQL Server
@enemyrr/mcp-mysql-服务器
提供 MySQL 数据库操作的模型上下文协议服务器。该服务器使 AI 模型能够通过标准化接口与 MySQL 数据库交互。
Cursor IDE 的安装和设置
通过 Smithery 安装
要通过Smithery自动为 Claude Desktop 安装 MySQL 数据库服务器:
npx -y @smithery/cli install @enemyrr/mcp-mysql-server --client claude手动安装
克隆并构建项目:
git clone https://github.com/enemyrr/mcp-mysql-server.git
cd mcp-mysql-server
npm install
npm run build在 Cursor IDE 设置中添加服务器:
打开命令面板(Cmd/Ctrl + Shift + P)
搜索“MCP:添加服务器”
填写字段:
名称:
mysql类型:
command命令:
node /absolute/path/to/mcp-mysql-server/build/index.js
注意:将
/absolute/path/to/替换为您克隆和构建项目的实际路径。
Related MCP server: MySQL MCP Server
数据库配置
您可以通过三种方式配置数据库连接:
.env 中的数据库 URL (推荐):
DATABASE_URL=mysql://user:password@host:3306/database.env 中的各个参数:
DB_HOST=localhost
DB_USER=your_user
DB_PASSWORD=your_password
DB_DATABASE=your_database通过工具直接连接:
use_mcp_tool({
server_name: "mysql",
tool_name: "connect_db",
arguments: {
url: "mysql://user:password@host:3306/database"
// OR
workspace: "/path/to/your/project" // Will use project's .env
// OR
host: "localhost",
user: "your_user",
password: "your_password",
database: "your_database"
}
});可用工具
1. 连接数据库
使用 URL、工作区路径或直接凭据连接到 MySQL 数据库。
2. 查询
使用可选的准备好的语句参数执行 SELECT 查询。
use_mcp_tool({
server_name: "mysql",
tool_name: "query",
arguments: {
sql: "SELECT * FROM users WHERE id = ?",
params: [1]
}
});3. 执行
使用可选的准备好的语句参数执行 INSERT、UPDATE 或 DELETE 查询。
use_mcp_tool({
server_name: "mysql",
tool_name: "execute",
arguments: {
sql: "INSERT INTO users (name, email) VALUES (?, ?)",
params: ["John Doe", "john@example.com"]
}
});4. 列表表
列出所连接数据库中的所有表。
use_mcp_tool({
server_name: "mysql",
tool_name: "list_tables"
});5. describe_table
获取特定表的结构。
use_mcp_tool({
server_name: "mysql",
tool_name: "describe_table",
arguments: {
table: "users"
}
});6. 创建表
创建具有指定字段和索引的新表。
use_mcp_tool({
server_name: "mysql",
tool_name: "create_table",
arguments: {
table: "users",
fields: [
{
name: "id",
type: "int",
autoIncrement: true,
primary: true
},
{
name: "email",
type: "varchar",
length: 255,
nullable: false
}
],
indexes: [
{
name: "email_idx",
columns: ["email"],
unique: true
}
]
}
});7. 添加列
向现有表中添加新列。
use_mcp_tool({
server_name: "mysql",
tool_name: "add_column",
arguments: {
table: "users",
field: {
name: "phone",
type: "varchar",
length: 20,
nullable: true
}
}
});特征
多种连接方式(URL、工作区、直接)
通过自动清理来安全处理连接
查询参数的预处理语句支持
架构管理工具
全面的错误处理和验证
TypeScript 支持
自动工作区检测
安全
使用准备好的语句来防止 SQL 注入
支持通过环境变量进行安全密码处理
执行前验证查询
完成后自动关闭连接
错误处理
服务器提供以下详细的错误消息:
连接失败
无效的查询或参数
缺少配置
数据库错误
架构验证错误
贡献
欢迎贡献!请随时向https://github.com/enemyrr/mcp-mysql-server提交 Pull 请求。
执照
麻省理工学院
Available Tools
7 toolsadd_columnC
Add a new column to existing table
Inputs: field (required), table (required).
connect_dbC
Connect to MySQL database using URL or config
Inputs: database, host, password, url, +2 more.
create_tableC
Create a new table in the database
Inputs: fields (required), table (required), indexes.
describe_tableB
Get table structure
Inputs: table (required).
executeC
Execute an INSERT, UPDATE, or DELETE query
Inputs: sql (required), params.
list_tablesB
List all tables in the database
Inputs: no named parameters.
queryC
Execute a SELECT query
Inputs: sql (required), params.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose with no ambiguity. For example, 'execute' handles INSERT/UPDATE/DELETE while 'query' handles SELECT, and 'describe_table' provides structure while 'list_tables' enumerates tables. The separation between schema operations (add_column, create_table) and data operations (execute, query) is well-defined.
All tools follow a consistent verb_noun pattern with clear, descriptive names. The naming convention is uniform throughout (e.g., add_column, create_table, describe_table, list_tables), making it easy to predict functionality. There are no deviations in style or formatting.
With 7 tools, this server is well-scoped for MySQL database operations. Each tool serves a specific, necessary function in the database management workflow, from connection (connect_db) to schema manipulation (create_table, add_column) and data querying (query, execute). The count avoids both bloat and insufficiency.
The tool set covers core MySQL operations effectively, including connection, schema management, and data querying. Minor gaps exist, such as the lack of tools for updating or deleting tables, which could limit full lifecycle management. However, agents can work around this using existing tools like 'execute' for DROP TABLE queries.
Maintenance
Related MCP Connectors
Work with your database from AI tools: ask, export, approved changes, and scheduled jobs.
Query Postgres, MySQL, SQL Server, Oracle, BigQuery, ClickHouse and Redshift from your AI client.
PostgreSQL, MySQL, and SQL Server in one session. 26 read-only MCP tools for AI agents.
Hosted MySQL MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI models to interact with MySQL databases through a standardized interface, supporting queries, data manipulation, table inspection, and query performance analysis with secure prepared statements.40 npm23MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI models to interact with MySQL databases through standardized operations including querying, executing commands, listing tables, and describing table structures with secure prepared statement support.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to securely connect to and manage MySQL databases with support for multiple database connections, complete CRUD operations, schema inspection, and dynamic connection management through natural language.19 npm81MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables AI assistants to securely interact with MySQL databases through tools for query execution, schema inspection, and transaction management. It features built-in safety controls like row limits and query validation to ensure safe and standardized database access.716 npm-