Atithi Driver Booking MCP Server
The Atithi Driver Booking MCP Server is an AI-powered system for managing cab bookings and driver dispatch for hotel guests, integrated with AI agents via the Model Context Protocol.
Driver Management: Onboard new drivers with personal, license, and vehicle details; verify registrations; update profiles, vehicle info, availability schedules, and real-time locations; list available drivers and retrieve full details including performance scores.
Hotel Preferred Drivers: Add/remove verified drivers to/from a hotel's preferred pool (with hotel manager authorization); list preferred drivers sorted by score for priority dispatch.
Pricing & Booking: Estimate fares based on pickup/drop locations, passenger count, and vehicle type; create guest bookings with optional pickup time and vehicle type; view booking status/location lists; cancel or complete bookings.
2-Tier Dispatch & Ride Lifecycle: Dispatching uses a priority algorithm: preferred hotel pool first, then global pool, matching seating capacity and ranked by driver score; record driver responses (accepted/rejected/no response) with timeouts; complete rides award +10 score, cancellations by driver incur -20 penalty; log call attempt histories.
Monitoring & Deployment: Driver scores adjust dynamically based on activities, with auto-suspension for low scores. The server is deployable via stdio, HTTP, or Docker for seamless AI agent integration.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Atithi Driver Booking MCP Server Book a cab for guest 203 to the airport and dispatch the nearest driver."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Atithi Driver Booking MCP Server
Production-ready Model Context Protocol (MCP) server for the Atithi Platform, providing an AI-powered automated driver dispatch and cab booking system for hotel guests.
Table of Contents
Related MCP server: Beckn Mobility MCP Server
Overview
The Atithi Driver Booking MCP Server allows AI Agents (like Claude Desktop or Voice Assistants) to seamlessly manage cab bookings, estimate fares using a $20 \times 20$ distance matrix, and dispatch cab drivers using a 2-tier priority matching algorithm (Hotel Preferred Pool $\rightarrow$ Global Pool).
Key Features
18 Automated MCP Tools: Covering driver onboarding, preferred hotel mapping, fare pricing, 2-tier dispatch, call attempt tracking, and ride lifecycle completion.
2-Tier Dispatch Algorithm: Prioritizes hotel preferred drivers before searching the global driver pool at the pickup location, ordered by driver performance score (
driver_score DESC).Driver Score & Penalty Engine: Dynamically awards points (+10 for completion) and applies penalties (-10 for rejection, -20 for driver cancellation) with auto-suspensions (<500 score).
Embedded SQLite Persistence: Fast, synchronous local database backed by
better-sqlite3.
Architecture
The server communicates via standard I/O (stdio) using JSON-RPC 2.0 protocol specifications defined by Anthropic's Model Context Protocol SDK.
AI Client (Claude Desktop / Voice AI)
│
├─► JSON-RPC over Stdio ──► MCP Server (dist/index.js)
│ │
│ ├─► Pricing Engine (Matrix Lookup)
│ ├─► 2-Tier Dispatch Algorithm
│ └─► SQLite Database (better-sqlite3)For detailed architectural diagrams and state machines, see docs/ARCHITECTURE.md.
Repository Structure
mcpserver3/
├── .gitignore # Git ignore rules
├── package.json # NPM scripts and dependencies
├── tsconfig.json # TypeScript compiler configuration
├── README.md # Project documentation
├── docs/ # Technical documentation
│ ├── ARCHITECTURE.md # Architectural design & PERSISTENCE
│ ├── TOOLS.md # Complete 18-tool API reference
│ ├── DB_AUDIT_REPORT.md # Database audit report
│ └── IMPLEMENTATION_PLAN.md # Implementation roadmap
├── src/ # TypeScript source code
│ ├── config/ # Configuration files
│ ├── tools/ # MCP Tool implementation handlers
│ │ ├── booking.ts # Booking creation & 2-Tier dispatch
│ │ ├── dispatch.ts # Call attempt logger & response status
│ │ ├── driver.ts # Driver onboarding & verification
│ │ ├── hotel.ts # Preferred driver mapping
│ │ ├── lifecycle.ts # Ride completion & penalties
│ │ ├── pricing.ts # Fare estimation & distance matrix
│ │ └── query.ts # System inspection & status queries
│ ├── db.ts # SQLite connection & auto-migrations
│ ├── idgen.ts # Primary key generators
│ ├── index.ts # Server entry point & stdio transport
│ ├── response.ts # ToolResult JSON envelope builders
│ ├── seed_distances.ts # 400 location pair distance seeder
│ ├── seed_expanded_dataset.ts # 150 Drivers & 150 Vehicles dataset generator
│ ├── setup_test_db.ts # Sandbox DB test seeder
│ ├── test.ts # 120-test integration test suite
│ ├── types.ts # TypeScript interfaces & DTO models
│ └── verify.ts # Verification suiteInstallation & Setup
Prerequisites
Node.js: v18.0.0 or higher
npm: v9.0.0 or higher
Step-by-Step Setup
Clone the repository:
git clone https://github.com/atithi/driver-booking-mcp.git cd driver-booking-mcpInstall dependencies:
npm installBuild the TypeScript source:
npm run build
Environment Configuration
The server supports the following environment variable and argument overrides:
Variable / Flag | Description | Default |
| Transport mode ( |
|
| HTTP server listening port (in |
|
| HTTP server bind host (in |
|
| Absolute path to the SQLite database file |
|
Build & Run Instructions
1. STDIO Mode (Claude Desktop & CLI)
Start MCP server (stdio transport):
npm startDevelopment mode (compile & start):
npm run dev
2. Streamable HTTP Mode (Atithi Platform Integration)
Start MCP server (Streamable HTTP transport on http://127.0.0.1:3000/mcp):
npm run start:httpCustom Port/Host via CLI flags:
node dist/index.js --transport=http --port=8080 --host=0.0.0.0
3. Docker Container Deployment
Build Production Docker Image:
docker build -t atithi-driver-booking-mcp:latest .Run Container (Default Streamable HTTP Mode on Port 3000):
docker run -d -p 3000:3000 --name atithi-mcp-server atithi-driver-booking-mcp:latestRun with Custom Host SQLite Database Volume Mounting:
docker run -d -p 3000:3000 \ -v /path/to/host/atithi_dummy_dataset.db:/app/atithi_dummy_dataset.db \ -e ATITHI_DB_PATH=/app/atithi_dummy_dataset.db \ --name atithi-mcp-server atithi-driver-booking-mcp:latestRun with Custom Port and Host Environment Overrides:
docker run -d -p 8080:8080 \ -e MCP_PORT=8080 \ -e MCP_HOST=0.0.0.0 \ --name atithi-mcp-server atithi-driver-booking-mcp:latestTest HTTP MCP Endpoint from Host:
curl -X POST http://127.0.0.1:3000/mcp \ -H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'
Verification & Testing
The repository contains an automated verification suite and an integration test suite covering 120 test cases.
Run Quick System Verification:
npm run verifyRun Full Integration Test Suite (120 Tests):
npm test
MCP Tools Summary
Category | Tools Included |
Driver Management |
|
Hotel Preferred |
|
Pricing & Booking |
|
Dispatch Logic |
|
Ride Lifecycle |
|
Queries & Inspection |
|
For full parameter details, refer to docs/TOOLS.md.
Integration with Claude Desktop
To connect this MCP server to Claude Desktop, add the following entry to your %APPDATA%\Claude\claude_desktop_config.json:
{
"mcpServers": {
"atithi-driver-booking": {
"command": "node",
"args": [
"C:/Users/satish u d/Desktop/atithiproject/mcpserver3/dist/index.js"
],
"env": {
"ATITHI_DB_PATH": "C:/Users/satish u d/Desktop/atithiproject/mcpserver3/atithi_dummy_dataset.db"
}
}
}
}Documentation & License
Architecture: docs/ARCHITECTURE.md
Tool Schemas: docs/TOOLS.md
License: MIT © Atithi Platform
Available Tools
20 toolsadd_preferred_driverA
Add a Verified driver to a hotel's preferred driver list. Caller must be a Hotel Manager for that hotel.
Inputs: hotel_id (required), driver_id (required), caller_user_id (required).
cancel_bookingA
Cancel a booking. If cancelled by Driver, applies a -20 score penalty. If no driver was found, set cancelled_by to 'No Driver Available'.
Inputs: booking_id (required), cancelled_by (required).
complete_bookingA
Mark a booking as completed when the guest reaches the destination. Frees the driver and awards +10 score.
Inputs: booking_id (required).
create_bookingA
Create a new guest ride booking with passenger count and estimated fare. Returns booking_id. Then call get_next_driver() to begin driver search.
Inputs: hotel_id (required), guest_name (required), booking_type (required), drop_location_id (required), +5 more.
estimate_fareA
Calculate distance and estimated fare in INR for a ride based on pickup, drop-off, passenger count, and vehicle type. Present this fare to the guest for confirmation before calling create_booking().
Inputs: drop_location_id (required), pickup_location_id (required), hotel_id, vehicle_type, +1 more.
get_booking_statusB
Get the current status and full details of a booking, including assigned driver info.
Inputs: booking_id (required).
get_driver_attempt_logA
Get the full call attempt history for a booking, ordered by attempt number.
Inputs: booking_id (required).
get_driver_detailsA
Get full profile, vehicle info, and performance score for a driver.
Inputs: driver_id (required).
get_hotel_preferred_driversA
Get all preferred drivers for a hotel, sorted by driver score.
Inputs: hotel_id (required).
get_locationsA
Get all available pickup/drop locations. Optionally filter by location type.
Inputs: location_type.
get_next_driverA
Get the next best available driver for a booking. Searches Preferred Pool first, then Global Pool, matching passenger seating capacity. Returns driver & full vehicle contact info.
Inputs: booking_id (required).
list_available_driversB
List all currently available Verified drivers. Optionally filter by current location.
Inputs: location_id.
register_driverB
Register a new driver and their vehicle in the Atithi system.
Inputs: email (required), phone (required), full_name (required), make_model (required), +5 more.
remove_preferred_driverA
Remove a driver from a hotel's preferred driver list. Caller must be a Hotel Manager for that hotel.
Inputs: hotel_id (required), driver_id (required), caller_user_id (required).
timeout_driver_attemptA
Record a 30-second timeout or dropped voice call for a driver. Automatically logs 'No Response' and returns next_action: GET_NEXT_DRIVER.
Inputs: driver_id (required), booking_id (required), pool_source.
update_driver_availabilityA
Replace a driver's entire weekly schedule. All existing entries are replaced.
Inputs: schedule (required), driver_id (required).
update_driver_detailsA
Update a driver's personal or vehicle details. Only provide fields you want to change.
Inputs: driver_id (required), email, phone, make_model, +5 more.
update_driver_locationB
Update a driver's current real-time location.
Inputs: driver_id (required), location_id (required).
update_driver_responseA
Record a driver's response to a booking call. Updates driver score. Returns next_action: RIDE_STARTED or GET_NEXT_DRIVER.
Inputs: response (required), driver_id (required), booking_id (required), pool_source (required), +2 more.
verify_driverB
Admin: Approve or reject a pending driver registration.
Inputs: decision (required), driver_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 20 tools
Each tool targets a distinct resource and action, such as driver registration/verification/updates, booking lifecycle, and queries. The workflow tools (get_next_driver, update_driver_response, timeout_driver_attempt) are clearly sequenced and separated.
All tool names follow a consistent verb_noun pattern in snake_case, e.g., verify_driver, create_booking, get_booking_status. There are no mixed conventions or vague verbs.
With 20 tools, the server is slightly above the typical 3-15 range, but each tool is necessary for the driver booking domain, covering driver management, booking workflow, and queries. The count is well-scoped for its purpose.
The tool set covers the full lifecycle: driver registration/verification/updates, booking creation, driver assignment, response handling, completion/cancellation, and a rich set of queries. No major gaps that would block core workflows.
Maintenance
Related MCP Connectors
Geocoding, routing, isochrones, traffic, weather, and place search for AI agents. 19 MCP tools.
Live hotel search and booking for AI agents in DACH, the UK and 10 US cities.
Operator-as-agent MCP hub. 6 tools. First $5 free, then $0.001/call.
Travel tools for AI agents: plan and edit real trips, search stays and tours, import travel videos.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables cab booking and management through natural conversation, allowing users to book rides, cancel bookings, and view driver details. Works with Google Maps MCP to provide comprehensive travel planning with automatic route optimization and cab arrangements between destinations.-
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to search for cabs, view prices, and book rides through the open Beckn Protocol by connecting to Beckn-compliant mobility providers like Namma Yatri and ONDC.-
- FlicenseAqualityCmaintenanceHotel booking MCP server — the first transaction-complete hotel booking integration for AI agents. Search 300K+ properties in 140+ countries, get live rates and room details, and generate secure checkout URLs. No payment in the AI conversation — guests complete booking at a hosted checkout page and receive a real hotel confirmation number. Set your own booking fee via Stripe Connect.830 npm3-

RollingGo Hotel MCPofficial
AlicenseNot gradedqualityCmaintenanceEnables AI agents to search, compare, and book hotels worldwide through natural language, with real-time pricing and availability, plus price monitoring and order management.60MIT