MapNAVI

参考小智的calculator MCP接入的高德MAP MCP

python

11

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "rickeylaiii-xiaoai_mapmcp": {
      "command": "python",
      "args": [
        "mcp_pipe.py",
        "map.py"
      ],
      "env": {
        "MCP_ENDPOINT": "<your_mcp_endpoint>"
      }
    }
  }
}

Xiaoai Map MCP is a map navigation MCP tool that integrates with map services to geocode addresses, fetch weather data, and plan driving routes. It expands your AI’s capabilities by connecting to external geographic information and routing resources through the MCP framework.

How to use

You interact with the Xiaoai Map MCP server through an MCP client to geocode locations, check weather, and plan driving routes. Use it to convert addresses to coordinates, retrieve current weather for a city or region, and generate driving directions between two points. The server exposes these capabilities as MCP endpoints you can request from your client.

How to install

Prerequisites: ensure you have Python 3.7 or later installed on your system.

Install project dependencies using the package file provided with the MCP setup.

pip install -r requirements.txt

Additional content

Environment variables:

MCP_ENDPOINT: specify your MCP server endpoint when connecting to the MCP network. Set it in your shell before running MCP-related commands.

export MCP_ENDPOINT=<your_mcp_endpoint>

Creating your own MCP tools

You can implement your own MCP tools by using a minimal example structure. Define a tool with a name and a function, then run the MCP pipeline to expose the tool via standard I/O.

from mcp.server.fastmcp import FastMCP

mcp = FastMCP("YourToolName")

@mcp.tool()
def your_tool(parameter: str) -> dict:
    """Tool description here"""
    # Your implementation
    return {"success": True, "result": parameter}

if __name__ == "__main__":
    mcp.run(transport="stdio")