
DB & Calculator MCP Server
A Model Context Protocol server providing tools for SQLite database operations (query, add, update, delete users) and mathematical calculations including basic arithmetic, expression evaluation, and statistical analysis.
README
MCP Example Server
This is a Model Context Protocol (MCP) server that provides two main categories of tools:
- Database Tools - For interacting with a SQLite database
- Calculator Tools - For performing mathematical calculations
Features
Database Tools
query_database
- Execute custom SQL queriesget_all_users
- Retrieve all users with optional limitget_user_by_id
- Get a specific user by IDadd_user
- Add a new user to the databaseupdate_user
- Update an existing userdelete_user
- Delete a user from the database
Calculator Tools
calculate
- Perform basic mathematical operations (add, subtract, multiply, divide, power, sqrt, sin, cos, tan, log, abs, round, floor, ceil)calculate_expression
- Evaluate mathematical expressionscalculate_stats
- Calculate statistical measures (mean, median, variance, standard deviation, etc.)
Installation
- Install dependencies:
npm install
- The database will be automatically created when you first run the server.
Usage
Starting the Server
npm start
Or for development with auto-restart:
npm run dev
Database Schema
The server creates a SQLite database with the following schema:
CREATE TABLE users (
id INTEGER PRIMARY KEY AUTOINCREMENT,
name TEXT NOT NULL,
email TEXT UNIQUE NOT NULL,
age INTEGER,
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
Sample data is automatically inserted when the database is first created.
Tool Examples
Database Operations
- Get all users:
{
"name": "get_all_users",
"arguments": {}
}
- Get user by ID:
{
"name": "get_user_by_id",
"arguments": {
"id": 1
}
}
- Add a new user:
{
"name": "add_user",
"arguments": {
"name": "John Doe",
"email": "john@example.com",
"age": 30
}
}
- Execute custom query:
{
"name": "query_database",
"arguments": {
"query": "SELECT * FROM users WHERE age > 25"
}
}
Calculator Operations
- Basic calculation:
{
"name": "calculate",
"arguments": {
"operation": "add",
"numbers": [5, 3]
}
}
- Evaluate expression:
{
"name": "calculate_expression",
"arguments": {
"expression": "2 + 3 * 4"
}
}
- Statistical analysis:
{
"name": "calculate_stats",
"arguments": {
"numbers": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
}
}
Available Calculator Operations
add
- Additionsubtract
- Subtractionmultiply
- Multiplicationdivide
- Division (with zero check)power
- Exponentiationsqrt
- Square rootsin
- Sine functioncos
- Cosine functiontan
- Tangent functionlog
- Natural logarithmabs
- Absolute valueround
- Round to nearest integerfloor
- Floor functionceil
- Ceiling function
Project Structure
├── package.json
├── README.md
├── src/
│ ├── server.js # Main MCP server
│ ├── database.js # Database operations
│ └── calculator.js # Calculator operations
└── data/
└── example.db # SQLite database (created automatically)
Error Handling
The server includes comprehensive error handling for:
- Invalid SQL queries
- Database connection issues
- Mathematical operation errors (division by zero, invalid inputs)
- Missing required parameters
- Unknown tool names
Development
To modify or extend the server:
- Add new tools in the
setupTools()
method inserver.js
- Implement corresponding handler methods
- Update the tools list in the
tools/list
handler - Add any necessary database operations in
database.js
- Add calculator functions in
calculator.js
Dependencies
@modelcontextprotocol/sdk
- MCP SDK for Node.jssqlite3
- SQLite database driverexpress
- Web framework (for potential future HTTP transport)
License
MIT
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。