MiniCab MCP
A Model Context Protocol server for a cab dispatch system that enables users to search available cabs, get fare estimates, book rides, and cancel bookings in supported cities.
README
MiniCab MCP
MiniCab MCP is a TypeScript Node.js backend for a small cab dispatch system exposed through the Model Context Protocol. It uses MySQL 8, raw SQL via mysql2, Zod validation, Pino logging, and the official @modelcontextprotocol/sdk.
Features
- MySQL schema with only the assignment tables: cities, drivers, vehicles, fare rules, bookings, and ledger.
- Fare rules support global defaults, time-of-day surge rows, and city-specific partial overrides without duplicating every vehicle type for every city.
- Hardcoded city route table for known pickup/drop points, as requested.
- MCP stdio server for Claude Desktop.
- Function-based repositories and services, with no app-owned classes or heavy framework abstractions.
- Transactional booking with
SELECT ... FOR UPDATEto prevent two users booking the same cab. - Server-side fare recalculation during booking.
- Ledger entry creation when a ride is completed.
- Jest tests for pure fare, route, and time helpers.
Requirements
- Node.js 18 or newer
- MySQL 8.0 or newer
- npm
Setup Without Docker
- Install dependencies:
npm install
- Create the database and seed it:
mysql -u root -p < schema.sql
mysql -u root -p < seed.sql
- Copy the environment file:
cp .env.example .env
-
Update
.envif your MySQL credentials differ. -
Build the project:
npm run build
- Start the MCP server:
npm start
The server uses stdio transport, so when Claude Desktop runs it, stdout is reserved for MCP protocol messages and logs go to stderr.
Claude Desktop Configuration
Build first with npm run build, then copy claude_desktop_config.example.json into your Claude Desktop config location and replace the placeholder path with your absolute project path.
Example:
{
"mcpServers": {
"minicab": {
"command": "node",
"args": [
"C:\\absolute\\path\\to\\minicab-mcp\\dist\\src\\index.js"
],
"env": {
"DB_HOST": "localhost",
"DB_PORT": "3306",
"DB_USER": "root",
"DB_PASSWORD": "root",
"DB_NAME": "minicab"
}
}
}
}
Restart Claude Desktop after saving the config.
MCP Tools
search_cabs
Searches available active vehicles in a city for a pickup/drop route and optional vehicle type.
Input:
{
"city": "Hyderabad",
"pickup": "Gachibowli",
"drop": "RGIA Airport",
"vehicle_type": "sedan"
}
get_fare_estimate
Returns fare estimates for all vehicle types without creating a booking.
Input:
{
"pickup": "Gachibowli",
"drop": "RGIA Airport",
"time": "18:00"
}
book_ride
Creates a confirmed booking for a specific cab. The server recalculates the fare and does not trust client-provided fare amounts.
Input:
{
"cab_id": 1,
"pickup": "Gachibowli",
"drop": "RGIA Airport",
"rider_name": "Mohd Tabrez"
}
cancel_ride
Cancels a confirmed booking and releases the vehicle.
Input:
{
"booking_id": 1
}
Tested Example Prompts
Prompt: "Get me a sedan from Gachibowli to the airport around 6pm in Hyderabad."
Expected tool call:
{
"tool": "search_cabs",
"arguments": {
"city": "Hyderabad",
"pickup": "Gachibowli",
"drop": "RGIA Airport",
"vehicle_type": "sedan"
}
}
Prompt: "How much would an SUV from Connaught Place to IGI Airport cost at 8:30am in Delhi?"
Expected tool call:
{
"tool": "get_fare_estimate",
"arguments": {
"pickup": "Connaught Place",
"drop": "IGI Airport",
"time": "08:30"
}
}
Prompt: "Book cab 1 for Mohd Tabrez from Gachibowli to RGIA Airport at 6pm."
Expected tool call:
{
"tool": "book_ride",
"arguments": {
"cab_id": 1,
"pickup": "Gachibowli",
"drop": "RGIA Airport",
"rider_name": "Mohd Tabrez"
}
}
Prompt: "Cancel booking 1."
Expected tool call:
{
"tool": "cancel_ride",
"arguments": {
"booking_id": 1
}
}
Tests
npm test
The included tests cover pure logic that does not need MySQL. A production submission should add integration tests with a disposable MySQL container for transaction and lock behavior.
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。