OneMap

You can run the OneMap MCP Server v2 locally or in the cloud to access Singapore's OneMap APIs via a Python-based MCP server. It exposes multiple tools for searching, geocoding, routing, coordinate conversions, planning areas, population data, nearby transport, and static maps, making it easy to build AI assistants and integrations that rely on OneMap data.

How to use

You will run the MCP server locally or in a deployment and connect your MCP client to it. Use the available tools to perform searches, geocode coordinates, convert coordinates between systems, retrieve thematic data, query planning areas and population data, find nearby transport options, and generate static maps. Start the server, then configure your client to call the required tools by name, passing the appropriate parameters like coordinates, search terms, or location identifiers. The server handles requests through the complete set of tools described in its feature set, returning structured responses that your AI assistant or application can consume.

How to install

Prerequisites You need Python 3.11 or newer and credentials from a OneMap account.

Local development steps follow. Copy and run each command in your terminal.

cd onemap-mcp
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -r requirements.txt
cp .env.example .env
# Edit .env with your OneMap credentials
python server.py

Environment variables and configuration

You configure credentials and options using a .env file. The following variables are required to run the server with OneMap authentication.

ONEMAP_EMAIL=your_email@example.com
ONEMAP_EMAIL_PASSWORD=your_password

Docker deployment

You can run the MCP server inside a Docker container. Build the image and run the container with the necessary environment variables.

docker build -t onemap-mcp .
docker run -d \
  -e ONEMAP_EMAIL="your_email@example.com" \
  -e ONEMAP_EMAIL_PASSWORD="your_password" \
  --name onemap-mcp \
  onemap-mcp

Azure deployment and cloud options

If you deploy to Azure, you can build a container image to a registry and run it in Container Apps or another service, using the same environment variables for authentication.

Available tools

search

Search for addresses, buildings, postal codes

reverse_geocode_wgs84

Get address from WGS84 coordinates

reverse_geocode_svy21

Get address from SVY21 coordinates

route_walk_drive_cycle

Walking, driving, cycling, barrier-free routes

route_public_transport

Bus and MRT routes with fare info

convert_4326_to_3857

WGS84 to Web Mercator conversion

convert_4326_to_3414

WGS84 to SVY21 conversion

convert_3414_to_4326

SVY21 to WGS84 conversion

convert_3414_to_3857

SVY21 to Web Mercator conversion

convert_3857_to_4326

Web Mercator to WGS84 conversion

convert_3857_to_3414

Web Mercator to SVY21 conversion

get_all_themes_info

List all 100+ thematic layers

get_theme_info

Get info about a specific theme

check_theme_status

Check if theme was updated

retrieve_theme

Retrieve theme data

get_all_planning_areas

Get all 55 planning area polygons

get_planning_area_names

List planning area names

get_planning_area_by_location

Get planning area for a location

get_population_age_group

Population by age

get_ethnic_distribution

Ethnic group distribution

get_economic_status

Employment statistics

get_household_monthly_income

Income distribution

get_education_status

Education levels

get_nearby_mrt_stations

Find nearby MRT/LRT stations

get_nearby_bus_stops

Find nearby bus stops

get_static_map

Generate map images with overlays