Install the Mireye Earth MCP server for agents

The Mireye Earth MCP server exposes the ask and fetch operations as native MCP tools. Install it once and any MCP-aware agent — Claude Desktop, Cursor, or your own Python client — can query geospatial data for US coordinates without writing HTTP code.

Claude Desktop
Cursor
Custom agent

Install the server

Install from GitHub using uv:

uv pip install 'mireye-earth[mcp] @ git+https://github.com/mireye/mireye-earth'

Or from a local clone:

uv pip install -e '.[mcp]'

Add the server to your Claude Desktop config

Edit the Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the mireye-earth entry under mcpServers:

{
  "mcpServers": {
    "mireye-earth": {
      "command": "mireye-earth-mcp"
    }
  }
}

Restart Claude Desktop

Restart Claude Desktop. Two tools appear under the 🔌 menu: ask and fetch.

Install the server

Install from GitHub using uv:

uv pip install 'mireye-earth[mcp] @ git+https://github.com/mireye/mireye-earth'

Or from a local clone:

uv pip install -e '.[mcp]'

Add the server to your Cursor MCP config

Edit the Cursor MCP config file:

Global: ~/.cursor/mcp.json
Workspace: <repo>/.cursor/mcp.json

Add the mireye-earth entry under mcpServers:

{
  "mcpServers": {
    "mireye-earth": {
      "command": "mireye-earth-mcp"
    }
  }
}

Confirm the tools are active

Open Cursor → Settings → MCP and confirm mireye-earth shows two green tools.

After installing the server (see the Claude Desktop tab for the install command), connect to it using the mcp Python SDK:

from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client

params = StdioServerParameters(command="mireye-earth-mcp")

async with stdio_client(params) as (read, write):
    async with ClientSession(read, write) as session:
        await session.initialize()
        tools = await session.list_tools()
        # tools.tools is [ask, fetch]

        result = await session.call_tool(
            "ask",
            {"lat": 40.7128, "lng": -74.0060, "question": "What is the elevation here?"},
        )

Configuration

Both tools share the same configuration, set via environment variables on the MCP server process:

Env var	Default	Purpose
`MIREYE_BASE_URL`	`https://mireye-earth.fly.dev`	HTTP base URL the tools POST to
`MIREYE_TIMEOUT_S`	`60`	Per-request timeout in seconds

Pass env vars to the server process through the env key in your MCP config:

{
  "mcpServers": {
    "mireye-earth": {
      "command": "mireye-earth-mcp",
      "env": {
        "MIREYE_BASE_URL": "https://your-deploy.example.com"
      }
    }
  }
}

Documentation Index

​Configuration

Configuration