yooztech_mcp_mysql
OfficialProvides secure read-only access to MySQL databases with automatic database inference from your project context. Uses parameterized queries, whitelisting, and rate limiting for safe querying.
Enables secure read-only access to MySQL databases with automatic database inference from project context. Provides safe querying capabilities with built-in security features like parameterized queries, whitelisting, and rate limiting.
What it does
- List available MySQL databases
- Infer database name from project files
- Query table schemas and structures
- Execute safe SELECT queries with parameterized inputs
- List tables within databases
- Rate limit queries with automatic LIMIT enforcement
Best for
About yooztech_mcp_mysql
yooztech_mcp_mysql is an official MCP server published by yooztech that provides AI assistants with tools and capabilities via the Model Context Protocol. Secure read-only MySQL access with automatic DB inference, parameterized queries, whitelisting and rate limiting — a saf It is categorized under databases.
How to install
You can install yooztech_mcp_mysql in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
License
yooztech_mcp_mysql is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
yooztech_mcp_mysql —— 基于 MCP 的 MySQL 工具（只读、安全、支持库推断）
该 MCP 服务器在 MCP 客户端中提供安全的 MySQL 读取能力：
list_databases()：列出当前账号可访问的非系统库infer_database(project_root=None, include_evidence=false)：根据项目内容推断库名（默认仅返回{ db }，可选返回最小化证据统计，不含文件路径/内容）list_tables(db=None)：列出库内表（未传db时使用已推断库或自动选择）get_table_schema(table, db=None)：获取表结构（列定义、主键、索引、表注释）select_rows(table, db=None, columns=None, where=None, order_by=None, limit=100)：从库表安全查询
安全设计
- 表/列白名单：从
information_schema动态获取并校验 - 参数化查询：拒绝拼接与多语句
- 限流：默认
LIMIT 100，最大LIMIT 1000 - 隐私：推断时不回传文件路径/内容；如需证据仅返回脱敏统计
在 Cursor 中配置
在 Cursor 的设置中添加 MCP Server，示例（仅示意，不包含本地路径）：
{
"mcpServers": {
"yooztech_mcp_mysql": {
"command": "yooztech_mcp_mysql",
"args": [],
"env": {
"DB_HOST": "127.0.0.1",
"DB_PORT": "3306",
"DB_USER": "mcp_tool",
"DB_PASS": "<your-strong-pass>"
}
}
}
}
说明：
- 以上配置假设你已通过包管理器安装本工具（例如
pip install yooztech_mcp_mysql），从而可直接使用控制台脚本yooztech_mcp_mysql。 - 若使用其他运行方式（如 uvx/容器），仅需将
command与args改为相应启动方式即可，但不要在 README 中暴露你的本地路径。
使用 uvx 方式（推荐，免安装）
如希望在不全局安装包的情况下运行，可在 Cursor 中使用 uvx：
{
"mcpServers": {
"yooztech_mcp_mysql": {
"command": "uvx",
"args": ["yooztech_mcp_mysql"],
"env": {
"DB_HOST": "127.0.0.1",
"DB_PORT": "3306",
"DB_USER": "mcp_tool",
"DB_PASS": "<your-strong-pass>"
}
}
}
}
提示：确保系统已安装 uv/uvx。企业私有镜像可通过 UV_INDEX/--index-url 进行加速配置。
环境变量
DB_HOST：数据库地址DB_PORT：数据库端口DB_USER：数据库只读账号（最小权限）DB_PASS：数据库密码
推荐在数据库中为该工具创建最小权限账号（示例）：
CREATE USER 'mcp_tool'@'10.0.%' IDENTIFIED BY '<your-strong-pass>';
GRANT SELECT ON *.* TO 'mcp_tool'@'10.0.%';
FLUSH PRIVILEGES;
如需进一步收紧权限，可按库或表粒度授予 SELECT。
使用建议（在 MCP 客户端中调用）
- 先调用
list_databases查看可访问库 - 再调用
infer_database自动推断当前项目使用的库（默认仅返回{ db }） - 随后调用
list_tables/select_rows（不传db时将使用推断库；如有歧义请显式传入db）
版本与许可证
- 版本遵循语义化版本（SemVer）
- 许可证：MIT（详见包内 LICENSE）
Alternatives
Related Skills
Browse all skillsConduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
Comprehensive guide for PostgreSQL psql - the interactive terminal client for PostgreSQL. Use when connecting to PostgreSQL databases, executing queries, managing databases/tables, configuring connection options, formatting output, writing scripts, managing transactions, and using advanced psql features for database administration and development.
Modern web development expertise covering React, Node.js, databases, and full-stack architecture. Use when: building web applications, developing APIs, creating frontends, setting up databases, deploying web apps, or when user mentions React, Next.js, Express, REST API, GraphQL, MongoDB, PostgreSQL, or full-stack development.
This skill should be used when the user requests to generate, create, or add Row-Level Security (RLS) policies for Supabase databases in multi-tenant or role-based applications. It generates comprehensive RLS policies using auth.uid(), auth.jwt() claims, and role-based access patterns. Trigger terms include RLS, row level security, supabase security, generate policies, auth policies, multi-tenant security, role-based access, database security policies, supabase permissions, tenant isolation.
Notion workspace integration. Use when user wants to read/write Notion pages, search databases, create tasks, or sync content with Notion.
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.