madurai-transit-mcp is the official Model Context Protocol (MCP) server for the Madurai CityBus public transit domain, with the goal of connecting AI assistants with Madurai's bus route network, official stage fares, stop sequences, and platform departure bay information. According to the repository description, it can connect to AI assistants such as Claude Desktop, Cursor, Gemini, and AI Agents.
Main capabilities
-
Route discovery: provides direct and one-transfer path planning across about 966 bus routes and about 3,000 stops.
-
Official stage fares: provides TNSTC official stage fare details, covering vehicle/service classes such as Ordinary, LSS, Express, and Deluxe AC.
-
Platform departure bay information: provides departure platform (I/II/III/IV) information for Periyar bus station.
-
Bilingual stop search: supports stop search in English, Tamil Unicode (such as பெரியார்), and colloquial transliteration.
-
Interactive deep links: automatically returns canonical links where a real-time visualized route map can be viewed (https://maduraione.in/route/...）。
Provided MCP tools
- search_bus_routes: find direct and one-transfer bus routes between two places in Madurai.
- get_bus_details: get complete route details, spoke classification, departure platform, and full stop sequence for a specified bus number.
- search_bus_stops: search bus stops bilingually in English and Tamil, and return spoke classification and verified GPS coordinates.
- Calculate exact official TNSTC stage fares for all service classes (Ordinary, LSS, Express, Deluxe AC).
How to use
The material provides access and testing methods:
- Claude Desktop: add the configuration to claude_desktop_config.json. The MacOS path is ~/Library/Application Support/Claude/claude_desktop_config.json; Windows is %APPDATA%\Claude\claude_desktop_config.json; Linux is ~/.config/Claude/claude_desktop_config.json.
- Cursor: add to .cursor/mcp.json, or configure in Cursor Settings ➔ Features ➔ MCP.
- Local testing: all tools can be tested interactively using the official MCP Inspector.
Applicable scenarios
Suitable for developers and users who need to integrate Madurai bus travel capabilities into AI assistants or AI agents, for example querying direct/one-transfer routes between two places, viewing the complete route and stop sequence by bus number, calculating official stage fares by vehicle class, confirming the departure platform at Periyar bus station, and searching stops in English or Tamil.
Limitations and notes
The repository clearly states that public transit in India's second-tier cities operates differently from Western bus models:
- Departure intervals and timetables: TNSTC Madurai buses operate by service departure intervals, not by published minute-by-minute numeric timetables.
- Topology and measured GPS: among about 3,000 stops across the region, about 600 core urban stops have verified measured coordinates; the remaining rural/suburban stops are topologically mapped in sequence.
- Multi-segment transfers:Transfer suggestions are based on the 7-Spoke Madurai topology model and should be used as a reference; passengers should verify real-time platform departures at the bus station.
Related links: Web app https://maduraione.in ; Android app (Google Play) is Madurai CityBus; GitHub repository https://github.com/rsiva2294/madurai-transit-mcp ; the project uses the MIT license, with copyright belonging to MaduraiOne. The material does not provide information on fees, prices, or paid plans.
