Expense Tracker MCP Server
Enables AI assistants to track, query, summarize, and delete personal expenses stored in a local SQLite database via natural language.
README
Expense Tracker MCP Server
A Model Context Protocol (MCP) server built with Python and FastMCP that allows LLM assistants (like Claude Desktop) to track, query, summarize, and delete personal expenses using a local SQLite database.
📌 Project Summary
This project provides an intelligent financial tracker backend accessible via MCP tools. With this MCP server, an AI assistant can manage your personal expenses directly through conversational prompts.
Available Resources:
config://categories: Provides a predefined JSON mapping of categories and sub-categories for both income and expenses.
Available Tools:
add_expense: Add a new expense with amount, category, optional description, and optional date.get_expenses: List and filter expenses by category, month, or year.delete_expense: Remove an expense record by its unique ID.add_income: Add a new income record (e.g., Salary, Investments).get_incomes: List and filter income records.delete_income: Remove an income record by its unique ID.get_summary: Generate a monthly summary grouped by spending and income categories.
🚀 Step-by-Step Setup & Implementation Guide
Prerequisites
- Python 3.10+
uv(Fast Python package installer and runner)- Claude Desktop (or any MCP-compliant client)
Step 1: Set Up the Project
Navigate to the project root directory:
cd C:\Users\arjun\Desktop\papi\expense-tracker-mcp
Install the required dependencies using uv:
uv pip install fastmcp
Step 2: Project Architecture (main.py)
The application defines an MCP server using FastMCP and initializes an SQLite database (expenses.db) automatically upon execution:
import datetime
from fastmcp import FastMCP
import os
import sqlite3
DB_PATH = os.path.join(os.path.dirname(__file__), "expenses.db")
mcp = FastMCP(name="Expense Tracker")
# Database Initialization
def init_db():
with sqlite3.connect(DB_PATH) as c:
c.execute('''
CREATE TABLE IF NOT EXISTS expenses (
id INTEGER PRIMARY KEY AUTOINCREMENT,
amount REAL NOT NULL,
category TEXT NOT NULL,
description TEXT,
date DATE NOT NULL DEFAULT CURRENT_DATE
)
''')
init_db()
Step 3: Test Running the MCP Server
You can run the server locally to ensure there are no syntax errors:
uv run python main.py
Step 4: Integrate with Claude Desktop
Option A: Automatic Installation (Standard Claude Desktop)
If using standard Claude Desktop:
uv run fastmcp install claude-desktop main.py
Option B: Manual Configuration (Windows Store Claude Desktop)
If using the Microsoft Store version of Claude Desktop, open your claude_desktop_config.json:
- Path:
%LOCALAPPDATA%\Packages\Claude_pzs8sxrjxfjjc\LocalCache\Roaming\Claude\claude_desktop_config.json
Add the server entry under mcpServers:
{
"mcpServers": {
"expense-tracker": {
"command": "uv",
"args": [
"run",
"python",
"C:\\Users\\arjun\\Desktop\\papi\\expense-tracker-mcp\\main.py"
]
}
}
}
Step 5: Restart Claude Desktop
- Close and fully quit Claude Desktop.
- Relaunch Claude Desktop.
- Look for the 🔌 icon to verify that the Expense Tracker tools are active.
💬 Example Conversational Prompts
Once configured in Claude Desktop, you can interact with your tracker using natural prompts:
- "Add an expense of $15.50 for lunch under Food category today."
- "Show all my Food expenses for this month."
- "Give me a spending summary for August 2026."
- "Delete expense ID 3."
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.