mcpField
S
SG Data MCP

SG Data MCP

Remote
github.com/vdineshkData & Analytics2Updated 29w ago
Repository

About SG Data MCP

SG Data MCP gives AI agents access to real-time Singapore government data and ACRA company records, spanning weather, environment, transport, and company lookup. Its MCP tools are available without an API key.

Key features

  1. 01Weather forecasts and UV readings
  2. 02PSI, PM2.5, and live rainfall
  3. 03Dengue cluster lookup
  4. 04HDB parking and taxi data
  5. 05ACRA company search and verification

Use cases

  1. 01Check local forecasts and air quality
  2. 02Find live parking availability or taxi data
  3. 03Search and verify ACRA-registered companies

MCP support

The MCP server exposes 13 real-time data tools to clients over Streamable HTTP, using data.gov.sg and ACRA data.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://sg-data-mcp.sgdata.workers.dev/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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

13

This tool takes no parameters.

Details

From the project README

SG Data MCP

Real-time Singapore government data and ACRA company intelligence for AI agents via the Model Context Protocol (MCP).

Live endpoint: https://sg-data-mcp.sgdata.workers.dev/mcp

What This Does

This MCP server gives any AI agent instant access to 13 real-time tools covering Singapore government data from data.gov.sg and ACRA company records. No API keys required for free tier.

Available Tools

Weather and Environment
ToolDescriptionSource
sg_weather_2h2-hour forecast by areaNEA
sg_weather_24h24-hour outlook with temp/humidity/windNEA
sg_weather_4day4-day forecast with daily conditionsNEA
sg_uv_indexReal-time UV exposure readingsNEA
sg_air_qualityPSI and PM2.5 by regionNEA
sg_rainfallLive rainfall from 50+ stationsNEA
sg_dengue_clustersActive dengue cluster locations and case countsNEA
Transport
ToolDescriptionSource
sg_carpark_availabilityLive HDB carpark lot availabilityHDB
sg_taxi_availabilityReal-time taxi count and locationsLTA
ACRA Company Intelligence
ToolDescriptionSource
sg_company_searchSearch companies by name - returns UEN, type, status, addressACRA
sg_company_uenLook up company by UEN numberACRA
sg_company_verifyVerify if a company exists and is activeACRA
sg_registered_entities_countTotal count of all ACRA-registered entitiesACRA

Quick Start

Connect via Streamable HTTP
Endpoint: https://sg-data-mcp.sgdata.workers.dev/mcp
Method: POST
Content-Type: application/json
Use in Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "sg-data": {
      "url": "https://sg-data-mcp.sgdata.workers.dev/mcp"
    }
  }
}
Example: Search Companies
curl https://sg-data-mcp.sgdata.workers.dev/mcp -X POST -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","method":"tools/call","id":1,"params":{"name":"sg_company_search","arguments":{"query":"DBS"}}}'
Example: Check Rainfall
curl https://sg-data-mcp.sgdata.workers.dev/mcp -X POST -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","method":"tools/call","id":1,"params":{"name":"sg_rainfall","arguments":{}}}'

Tech Stack

  • Runtime: Cloudflare Workers (edge, near-zero cold start)
  • Protocol: MCP over Streamable HTTP (JSON-RPC 2.0)
  • Data: data.gov.sg public APIs and ACRA open datasets
  • Cost: Free tier available

Roadmap

  • Malaysia SSM company registry
  • Indonesia AHU company registry
  • Bus/MRT arrival times (LTA DataMall)
  • URA property transaction data
  • OneMap geocoding
  • API key gating for premium tier
  • Stripe MPP integration for agent-to-agent payments

Author

Dinesh Kumar - Singapore - [email protected]

License

MIT

Comments

Markdown supported

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.