AWS-GeoPlaces-MCP-Server

Directly access AWS location services using the GeoPlaces v2 API, provides geocoding or reverse-geocoding capabilities like the Google Maps API.

Prerequisites

1. AWS Permissions needed to host MCP for Location Service, Refer to the example json file for the minimum viable permissions.

Development

1. Install uv for Python project management:

   MacOS / Linux:

   curl -LsSf https://astral.sh/uv/install.sh | sh
   

   Windows:

   powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
   

2. Create a virtual environment

   uv venv --python 3.13
   

3. Start the virtual environment

   source .venv/bin/activate
   

   NOTE: To stop the virtual environment:

   deactivate
   

4. Install MCP Python SDK and AWS boto3 client:

   uv add "mcp[cli]"
   uv add "boto3"
   uv add "python-dotenv"
   

Quickstart

1. Create your MCP using Python

2. Run your server in the MCP Inspector:

   mcp dev server.py
   

3. Install the server in Claude Desktop:

   mcp install <your_server_name.py>
   

4. Open claude_desktop_config.js in an editor: From Claude:

   1. Open Claude
   2. Go to Settings
   3. In the pop-up, select “Developer”
   4. Click “Edit Config”

   File location:

   • MacOS / Linux ~/Library/Application/Support/Claude/claude_desktop_config.json
   • Windows AppDataClaudeclaude_desktop_config.json

5. Find the full path to uv: MacOS / Linux:

   which uv
   

   Windows:

   where uv
   

6. In claude_desktop_config.js, set the command property to the full uv path for your MCP Server Example:

   "weather": {
      "command": "/absolute/path/to/uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "mcp",
        "run",
        "/absolute/path/to/your/server.py"
      ]
    },
   

7. Reboot Claude Desktop and use a prompt that will trigger your MCP.