About Indian Railways IRCTC
A remote MCP server for information about Indian Railways, covering train searches, routes, live status, station boards, and PNR status. It provides travel information but does not book, pay for, or cancel tickets.
Key features
- 01Search trains by route and date
- 02View train routes and stops
- 03Check live train running status
- 04View station arrival and departure boards
- 05Check PNR status
Use cases
- 01Find trains between stations
- 02Check a train's current position
- 03Review station arrivals and departures
- 04Check ticket status using a PNR
MCP support
Exposes Indian Railways information tools through a remote Streamable HTTP MCP server. OAuth 2.1 sign-in is supported; ticket booking, payment, and cancellation are not provided.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://transport-agent-claude.saifs.ai/mcpclaude mcp add --transport http ai-saifs-indian-railways-irctc https://transport-agent-claude.saifs.ai/mcp{"mcpServers":{"ai-saifs-indian-railways-irctc":{"type":"http","url":"https://transport-agent-claude.saifs.ai/mcp"}}}Open in Cursor{"servers":{"ai-saifs-indian-railways-irctc":{"type":"http","url":"https://transport-agent-claude.saifs.ai/mcp"}}}Open in VS Code{"mcpServers":{"ai-saifs-indian-railways-irctc":{"type":"http","url":"https://transport-agent-claude.saifs.ai/mcp"}}}{"mcpServers":{"ai-saifs-indian-railways-irctc":{"serverUrl":"https://transport-agent-claude.saifs.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEIndian Railways IRCTC
Information-only Indian Railways assistant: find trains between stations (with or without a date), see full routes and stops, live running status, station arrival/departure boards and PNR status. It does not book, pay for or cancel tickets.
| Registry name | ai.saifs/indian-railways-irctc |
| Endpoint | https://transport-agent-claude.saifs.ai/mcp |
| Transport | Streamable HTTP (remote, nothing to install) |
| Auth | OAuth 2.1 — PKCE (S256) and dynamic client registration; your client opens a sign-in page on first use |
| Publisher | SAIFS AI |
Install
VS Code / GitHub Copilot
Add to .vscode/mcp.json (workspace) or your user mcp.json:
{
"servers": {
"saifs-indian-railways": {
"type": "http",
"url": "https://transport-agent-claude.saifs.ai/mcp"
}
}
}
Then start the server from the MCP view and sign in when prompted.
Claude (claude.ai, Desktop)
Settings → Connectors → Add custom connector, and paste:
https://transport-agent-claude.saifs.ai/mcp
Claude Code
claude mcp add --transport http saifs-indian-railways https://transport-agent-claude.saifs.ai/mcp
Any other MCP client
Point it at https://transport-agent-claude.saifs.ai/mcp using the Streamable HTTP transport. The server returns 401 with a
WWW-Authenticate: Bearer … resource_metadata=… challenge, so OAuth-aware clients sign in automatically.
Tools
| Tool | What it does |
|---|---|
railway_train_getByNumber | Train details for a 5-digit train number. |
railway_train_searchByRouteDate | Trains, classes and availability between two stations on a date (DD-MM-YYYY, up to 60 days ahead). |
railway_train_betweenStations | Trains between two station codes, no date needed. |
railway_train_route | Full route and stops of a train. |
railway_train_liveStatus | Current running status and position of a train. |
railway_station_liveBoard | Arrivals and departures board for a station. |
railway_train_pnrStatus | Status of a 10-digit PNR. |
Example prompts
- “Which trains go from Ratlam (RTM) to Mumbai Central (MMCT) on 05-11-2026?”
- “Where is train 12961 right now?”
- “Check PNR 2832453235.”
Support
- Website: https://saifs.ai
- Issues: https://github.com/Saify-Technologies/saifs-ai-mcps-docs/issues
- Privacy: https://saifs.ai/privacy_policy
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.