Back to Portfolio
2025
MCPAI AgentsPythonAPIs

AbhiBus MCP Booking Server

"Built an MCP (Model Context Protocol) server that lets AI agents like Claude search cities, find buses, view live seat layouts, apply discounts, and create real bookings with payment links — bringing conversational AI booking to the bus category."

Executive Summary

A Model Context Protocol server that exposes AbhiBus's booking stack to AI assistants. An agent can search source/destination cities, list buses with fares, inspect seat layouts, check applicable discounts, and generate a real booking with a payment link — end to end, in one conversation. Works out of the box with Claude Desktop.

Key Outcomes

  • Full bus booking flow (search → seats → discounts → payment link) usable by AI agents.
  • Works out of the box with Claude Desktop via MCP configuration.
  • Turned internal booking APIs into safe, structured tools for LLMs.
  • Positioned AbhiBus early in the agentic-commerce channel.

Next Case Study

The AI-Operated Growth Stack

Built 20+ custom AI agent skills that teach Claude and Codex to operate the entire growth stack — Google Ads, Meta Ads, CleverTap, WhatsApp (Gupshup), ClickHouse data, n8n workflows, deployments, Jira, Slack, and Gmail. The result: growth ops that run on natural language.