A Model Context Protocol server for Singapore transport data with real-time information and routing
MCP Public Transport MCP server exists for a simple reason — assistants are far more useful when they can act on MCP Public Transport directly instead of describing what you should do. A Model Context Protocol server for Singapore transport data with real-time information and routing.
As the creator of this project, I, Siva (Sivasubramanian Ramanathan), developed this comprehensive Singapore Location Intelligence Platform to explore the capabilities of the Model Context Protocol (MCP). My goal was to test how MCP could be leveraged to help AI accurately plan routes, while also showcasing my ability to work with various APIs and my expertise in the technologies involved.
The server ships on npm as @siva-sub/mcp-public-transport, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Once MCP Public Transport is connected, these are the calls the assistant has available:
Real — time Data**: Rainfall, temperature, humidity, wind speedLocation-based — Weather conditions for specific route segmentsInstallation — The Installation tool exposed by this serverBuilding — The Building tool exposed by this serverTesting — The Testing tool exposed by this serverYou will need 4 environment variables: LTA_ACCOUNT_KEY, ONEMAP_TOKEN, ONEMAP_EMAIL, ONEMAP_PASSWORD. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP Public Transport's toolset — Real, Location-based, Installation and 2 more — is a fair guide to whether it matches your workflow. It is maintained by siva-sub; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against MCP Public Transport's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Real | time Data**: Rainfall, temperature, humidity, wind speed |
| Location-based | Weather conditions for specific route segments |
| Installation | The Installation tool exposed by this server. |
| Building | The Building tool exposed by this server. |
| Testing | The Testing tool exposed by this server. |
{
"mcpServers": {
"public-transport": {
"command": "npx",
"args": ["-y", "@siva-sub/mcp-public-transport"],
"env": {
"LTA_ACCOUNT_KEY": "your-value",
"ONEMAP_TOKEN": "your-value",
"ONEMAP_EMAIL": "your-value",
"ONEMAP_PASSWORD": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| LTA_ACCOUNT_KEY | Credential the server authenticates with. | Yes |
| ONEMAP_TOKEN | Credential the server authenticates with. | Yes |
| ONEMAP_EMAIL | Configuration value read at startup. | Optional |
| ONEMAP_PASSWORD | Configuration value read at startup. | Optional |
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Inbox intelligence — search, read, draft and send Gmail through your assistant with OAuth auto-setup.
Read and write Jira, Confluence, Bitbucket, JSM and Compass from your AI client — with your own permissions.
Read and send Telegram messages through your assistant — chats, channels and history via the client API.
Enables Discord bot integration with Model Context Protocol (MCP) compatible applications like Claude Desktop.
Exposes REST APIs defined by OpenAPI specifications as Model Context Protocol (MCP) tools, facilitating seamless integration into MCP-based workflows.