Expense Tracker MCP Proxy for Remote Server

A Model Context Protocol (MCP) proxy server that connects to a remote expense tracker FastMCP cloud server and exposes its tools locally.

Note: This is a proxy server only. It connects to a remote FastMCP cloud URL and forwards requests to the actual expense tracking implementation. The source code for the expense tracking functionality is available at: expense-tracker-remote-mcp-server

Features

This proxy server:

• Connects to the remote FastMCP server at https://chronic-scarlet-urial.fastmcp.app/mcp

• Automatically discovers and exposes all tools available on the remote server

• Forwards all tool calls to the remote server

• Provides transparent proxying with error handling

• Handles Server-Sent Events (SSE) responses from the FastMCP server

• Acts as a local stdio interface to the remote expense tracker implementation

Remote Server Tools

The remote FastMCP server provides an Expense Tracker with 5 tools:

• add_expense: Add a new expense with date, amount, category, subcategory, and notes

• list_expenses: List expenses with optional filtering by category and date range

• update_expense: Update an existing expense

• delete_expense: Delete an expense

• summarize_expenses: Get expense summaries grouped by category

Installation

1. Install dependencies:

pip install -e .

Or install manually:

pip install mcp aiohttp

Usage

Run the server:

python main.py

The server communicates via stdio and follows the Model Context Protocol specification.

Configuration

To use this server with an MCP client (like Claude Desktop), add it to your client configuration:

{
  "mcpServers": {
    "bhakti-server-proxy": {
      "command": "python",
      "args": ["d:\\Python Projects\\Proxy-server\\main.py"]
    }
  }
}

Or with the full Python path:

{
  "mcpServers": {
    "bhakti-server-proxy": {
      "command": "C:\\Users\\kulsu\\AppData\\Local\\Programs\\Python\\Python314\\python.exe",
      "args": ["d:\\Python Projects\\Proxy-server\\main.py"]
    }
  }
}

Development

The server is built using the mcp Python library and implements:

• Tool listing from remote server

• Tool execution forwarding to remote server

• Async stdio communication

• Server-Sent Events (SSE) handling

Testing

Test the connection to the remote server:

python test_proxy.py

License

MIT