提供 PostgreSQL 数据库管理功能的模型上下文协议 (MCP) 服务器。该服务器可协助分析现有 PostgreSQL 设置、提供实施指导以及调试数据库问题。
analyze_database ）分析 PostgreSQL 数据库配置和性能指标：
配置分析
性能指标
安全评估
优化建议
// Example usage
{
"connectionString": "postgresql://user:password@localhost:5432/dbname",
"analysisType": "performance" // Optional: "configuration" | "performance" | "security"
}get_setup_instructions ）提供分步 PostgreSQL 安装和配置指南：
特定于平台的安装步骤
配置建议
安全最佳实践
安装后任务
// Example usage
{
"platform": "linux", // Required: "linux" | "macos" | "windows"
"version": "15", // Optional: PostgreSQL version
"useCase": "production" // Optional: "development" | "production"
}debug_database ）调试常见的 PostgreSQL 问题：
连接问题
性能瓶颈
锁冲突
复制状态
// Example usage
{
"connectionString": "postgresql://user:password@localhost:5432/dbname",
"issue": "performance", // Required: "connection" | "performance" | "locks" | "replication"
"logLevel": "debug" // Optional: "info" | "debug" | "trace"
}Related MCP server: Postgres MCP Pro
Node.js >= 18.0.0
PostgreSQL 服务器（用于目标数据库操作）
对目标 PostgreSQL 实例的网络访问
要通过Smithery自动为 Claude Desktop 安装 PostgreSQL MCP 服务器：
npx -y @smithery/cli install @nahmanmate/postgresql-mcp-server --client claude克隆存储库
安装依赖项：
npm install构建服务器：
npm run build添加到 MCP 设置文件：
{
"mcpServers": {
"postgresql-mcp": {
"command": "node",
"args": ["/path/to/postgresql-mcp-server/build/index.js"],
"disabled": false,
"alwaysAllow": []
}
}
}npm run dev - 使用热重载启动开发服务器
npm run lint - 运行 ESLint
npm test运行测试
连接安全
使用连接池
实现连接超时
验证连接字符串
支持 SSL/TLS 连接
查询安全
验证 SQL 查询
防止危险操作
实现查询超时
记录所有操作
验证
支持多种身份验证方法
实现基于角色的访问控制
执行密码策略
安全地管理连接凭证
始终使用具有适当凭据的安全连接字符串
遵循敏感环境的生产安全建议
定期监控和分析数据库性能
保持 PostgreSQL 版本为最新版本
实施适当的备份策略
使用连接池实现更好的资源管理
实施适当的错误处理和日志记录
定期安全审核和更新
服务器实现了全面的错误处理：
连接失败
查询超时
身份验证错误
权限问题
资源限制
evals 包会加载一个 mcp 客户端，然后运行 index.ts 文件，因此测试之间无需重新构建。您可以在此处查看完整文档。
OPENAI_API_KEY=your-key npx mcp-eval src/evals/evals.ts src/index.ts分叉存储库
创建功能分支
提交你的更改
推送到分支
创建拉取请求
该项目根据 AGPLv3 许可证获得许可 - 有关详细信息，请参阅 LICENSE 文件。
Analyze PostgreSQL database configuration and performance
Inputs: connectionString (required), analysisType.
Debug common PostgreSQL issues
Inputs: connectionString (required), issue (required), logLevel.
Get step-by-step PostgreSQL setup instructions
Inputs: platform (required), version, useCase.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool has a clearly distinct purpose: analyze_database focuses on configuration and performance analysis, debug_database targets issue troubleshooting, and get_setup_instructions provides installation guidance. There is no overlap in functionality, making it easy for an agent to select the appropriate tool without confusion.
All tool names follow a consistent verb_noun pattern (analyze_database, debug_database, get_setup_instructions), using snake_case throughout. The naming is predictable and readable, with no deviations or mixed conventions.
With only 3 tools, the server feels thin for a PostgreSQL domain, which typically involves operations like querying, inserting, updating, or managing tables. While the tools cover analysis, debugging, and setup, the lack of core database interaction tools suggests an incomplete surface for typical agent workflows.
The tool set is severely incomplete for a PostgreSQL server, as it lacks basic CRUD operations (e.g., execute_query, create_table, insert_data) and management functions (e.g., list_tables, backup_database). This will cause significant agent failures when attempting to interact with the database beyond setup and diagnostics.
Comprehensive PostgreSQL documentation and best practices, including ecosystem tools
Hosted MCP server for PostgreSQL diagnostics: slow queries, missing indexes, connection pressure.
Hosted PostgreSQL MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Query PostgreSQL databases in plain English — LLM-generated, safety-validated SQL.
