Querysharp MCP Server
Enables AI assistants to analyze and optimize PostgreSQL database performance by identifying missing indexes and suggesting query rewrites. It allows users to retrieve database projects and implement performance fixes directly through natural language in their code editor.
README
Querysharp MCP Server
A Model Context Protocol (MCP) server for Querysharp, enabling AI assistants to help you analyze and optimize your PostgreSQL database performance directly from your code editor.
🚀 Quick Start
Setup in Cursor/Claude
Add to your MCP configuration file:
{
"mcpServers": {
"querysharp": {
"command": "npx",
"args": ["querysharp-mcp", "--api-key", "YOUR_API_KEY"]
}
}
}
For global installation:
{
"mcpServers": {
"querysharp": {
"command": "querysharp-mcp",
"args": ["--api-key", "YOUR_API_KEY"]
}
}
}
🎯 What It Does
Querysharp is a database performance monitoring tool that identifies potential performance issues and suggests optimizations. This MCP server allows AI assistants like Claude (in Cursor) to:
- 🔍 Get your database projects - Retrieve all monitored databases
- 🛠️ Fetch performance fixes - Get specific optimization recommendations
- 🚀 Apply optimizations - Let AI help implement the suggested fixes
🛠️ Features
Available Tools
get_projects- Lists all your Querysharp projects with their database tablesget_database_fixes- Retrieves performance fixes for a specific project, including:- Missing index recommendations with SQL commands
- Query rewrite suggestions for better performance
- Severity levels (Low, Medium, High, Critical)
🔧 Requirements
- Node.js: 18.0.0 or higher
- Querysharp Account: Free signup at querysharp.com
- PostgreSQL Database: Connected to Querysharp for monitoring
🔧 Getting Your API Key
- Sign up at Querysharp
- Add your PostgreSQL database for monitoring
- Get your API key from the dashboard
💬 Usage Examples
Once configured, you can ask your AI assistant questions like:
- "What database performance issues do I have?"
- "Show me the missing indexes for my production database"
- "Help me optimize my slow queries"
- "Fix my database performance problems"
Example Interaction
You: "Help me fix my database performance"
AI: Let me check your Querysharp projects and get the performance fixes...
[AI calls get_projects tool]
[AI calls get_database_fixes tool for your project]
AI: I found 3 performance issues in your database:
1. **Missing Index on users.email** (HIGH severity)
- Table: users
- Suggested SQL: `CREATE INDEX idx_users_email ON users(email);`
2. **Slow JOIN Query** (MEDIUM severity)
- Original: `SELECT * FROM orders JOIN users ON...`
- Optimized: `SELECT o.id, u.name FROM orders o JOIN users u ON...`
Would you like me to help you implement these fixes?
🤝 Contributing
We welcome contributions! Please see our Contributing Guide for details.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
License Scope
What this MIT license covers:
- ✅ This MCP server code and implementation
- ✅ All code in this repository
What this license does NOT cover:
- ❌ Querysharp's main database monitoring service
- ❌ Querysharp's proprietary algorithms and analysis
- ❌ Querysharp's web dashboard and API backend
- ❌ Any Querysharp intellectual property
- ❌ Anything outside of this repository
Note: This MCP server is a client that connects to Querysharp's API service. You still need a valid Querysharp account and API key to use this tool. Querysharp's terms of service apply to your use of their API and service.
🔗 Links
- 🌐 Website: querysharp.com
- 🐛 Issues: GitHub Issues
- 💬 Support: thomas@weepulse.fr
🏷️ Keywords
mcp, model-context-protocol, database, performance, postgresql, querysharp, optimization, sql, missing-indexes, query-optimization, cursor, claude
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。