ExpenseTracker

Provides a local MCP backend to persist, analyze, and export expense data via PostgreSQL.

python

0

GitHub Stars

python

Language

6 months ago

First Indexed

3 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": {
    "tanishra-expense-tracker-mcp": {
      "command": "uv",
      "args": [
        "run",
        "fastmcp",
        "dev",
        "main.py"
      ],
      "env": {
        "DB_HOST": "localhost",
        "DB_NAME": "expense_tracker",
        "DB_PORT": "5432",
        "DB_USER": "expense_user",
        "DB_PASSWORD": "YOUR_PASSWORD"
      }
    }
  }
}

ExpenseTracker MCP Server turns your AI assistant into a persistent personal finance manager by securely storing, analyzing, and exporting expense data in PostgreSQL. It provides structured financial tools to enable long-term data retention and robust reporting without relying on chat memory.

How to use

You connect your MCP-enabled assistant to the ExpenseTracker MCP Server to store expenses permanently, edit or delete records, and generate insights. Your assistant can summarize spending, identify top categories, produce monthly reports, and export data for accounting or tax use. Interactions are performed against a real database, so results reflect your actual data rather than memory.

Typical workflows include adding new expenses, updating existing entries, querying summaries for a given month, and exporting data for external accounting. The server responds with structured results that you can feed back into your assistant’s UI or workflows.

How to install

Prerequisites you need before installing the MCP server:

Python 3.8+ installed on your machine.
A running PostgreSQL instance reachable from your machine.
The MCP runtime tool uv installed and available on your PATH.

Follow these concrete steps to set up and run the server locally:

uv add fastmcp psycopg2-binary python-dotenv

DB_HOST=localhost
DB_PORT=5432
DB_NAME=expense_tracker
DB_USER=expense_user
DB_PASSWORD=your_password

uv run fastmcp dev main.py

uv run fastmcp run main.py

uv run fastmcp install claude-desktop main.py

Restart Claude Desktop after starting the server.

## Additional notes

Environment variables shown in the example .env file are required for the server to connect to PostgreSQL. Keep these credentials secure and do not commit them to public repositories.

If you need to connect Claude Desktop, use the provided installation command to link the desktop client to the MCP server. Restart the desktop client after installation to establish the connection.

## Available tools

### store\_expense

Persist a new expense entry in PostgreSQL with details like amount, date, category, and notes.

### edit\_expense

Modify fields of an existing expense record, such as amount, date, or category.

### delete\_expense

Remove an expense record from the database.

### summarize\_spending

Provide a summary of total spending over a specified period and by category.

### top\_categories

Identify the categories with the highest spending in a given timeframe.

### monthly\_report

Generate a structured report for a given month with totals by category and graphs-ready data.

### export\_data

Export expenses to a file format suitable for accounting or tax use.