Amap

You can run the Amap MCP Server to provide geocoding, routing, POI search, and other location-based services to AI agents via the MCP protocol. This server architecture lets you leverage Amap capabilities through a consistent tool interface for your autonomous workflows and LLM-enabled applications.

How to use

To use the Amap MCP Server, start it as a local MCP tool and connect your MCP client to it through stdio. You can run it directly or via the MCP CLI. Once running, your client can request geocoding, route planning, POI search, and administrative or IP-based location features using the exposed tools.

How to install

Prerequisites: ensure Python is installed on your system. You also need an API key from Amap to access the services.

# 1) Install dependencies using pip
pip install -r requirements.txt

# 2) Optional: install with uv (recommended for faster startup)
uv pip install -r requirements.txt

Additional configuration and start steps

Set up environment variables and start the MCP server using either of the provided commands. You can run the server directly with Python or via the MCP CLI.

# Option A: Run the MCP server directly
python amap_mcp.py

# Option B: Run via the MCP CLI
mcp run amap_mcp.py

Environment setup and API key

Prepare your environment by providing your Amap API key. You can either copy the example config and fill in the key, or create a new .env file with the required variable.

# Copy the template and edit
cp .env.example .env
# Edit .env to set AMAP_API_KEY=your_amap_api_key_here

Connecting from a client

Connect your MCP client to the running server using the stdio transport. The server exposes tools for geocoding, routing, and POI search that your client can invoke with the appropriate parameters.

Security note

Keep your API key secure. Do not commit your .env file to version control and restrict access to servers running the MCP endpoint.

Available tools

geocoding

Convert addresses to coordinates and vice versa using the Amap geocoding services.

reverse_geocoding

Retrieve a human-readable address from a set of coordinates.

driving_route_planning

Plan driving routes with various strategies such as fastest, shortest, or cost-optimized options.

walking_route_planning

Compute walking routes, including indoor/outdoor routing where available.

bicycling_route_planning

Generate bicycle-friendly routes.

elect_bike_route_planning

Plan routes optimized for electric bikes, including charging considerations.

public_transit_route_planning

Plan routes using public transit, including subway and bus transfers.

amap_route_subway

Provide subway routing within a city.

search_poi

Keyword-based POI search.

search_poi_around

Around search for POIs near a location.

search_poi_polygon

POI search within a polygon area.

search_poi_detail

Retrieve detailed information about a POI.

search_aoi_boundary

Query AOI (Area Of Interest) boundaries.

administrative_region_query

Query administrative region data.

ip_positioning

Determine location based on IP address.