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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.