Expense Tracker MCP Server
Enables AI assistants to manage personal expenses through natural conversation, supporting expense tracking, categorization, filtering, and financial summaries. Uses SQLite database to store expense records with full CRUD operations for comprehensive personal finance management.
README
Expense Tracker MCP Server
A Model Context Protocol (MCP) server that enables AI assistants like Claude to manage your personal expenses through natural conversation. Built with Python using fastmcp and uv.
Features
- Add Expenses: Record expenses with amount, category, date, and description
- List & Filter: View expenses by category and date range
- Summarize: Get spending summaries grouped by category
- Update Expenses: Modify existing expense records
- Delete Expenses: Remove unwanted expense entries
- Natural Language Interface: Interact with your expense data conversationally through Claude
Prerequisites
- Python 3.10 or higher
- uv package manager
Installation
# Clone the repository
git clone https://github.com/Khushi-c-sharma/expense-tracker-mcp-server.git
cd expense-tracker-mcp-server
# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh
# Install dependencies
uv sync
Configuration
Add the server to your Claude Desktop configuration file:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"expense-tracker": {
"command": "uv",
"args": [
"--directory",
"/path/to/expense-tracker-mcp",
"run",
"expense-tracker"
]
}
}
}
Usage Examples
Once configured, you can interact with your expenses through Claude naturally:
You: "Add expense 2632 spent yesterday for shopping dress for my convocation"
Claude: *Adds the expense with proper categorization*
You: "Show me all my expenses this month"
Claude: *Lists and summarizes your monthly expenses*
You: "How much did I spend on food in September?"
Claude: *Provides category-specific spending summary*
Available Tools
add_expense
Add a new expense to the database.
- Parameters: amount (required), category (required), date, description, subcategory
list_expenses
List expenses filtered by category and optional date range.
- Parameters: category, start_date, end_date
summarize
Get total expenses by category within a date range.
- Parameters: start_date (required), end_date (required), category
update_expense
Update an existing expense.
- Parameters: expense_id (required), amount, category, date, description, subcategory
delete_expense
Delete an expense by ID.
- Parameters: expense_id (required)
Database
Expenses are stored in a local SQLite database (expenses.db) with the following schema:
CREATE TABLE expenses (
id INTEGER PRIMARY KEY AUTOINCREMENT,
amount REAL NOT NULL,
category TEXT NOT NULL,
subcategory TEXT,
date TEXT NOT NULL,
description TEXT
);
Development
# Run the server directly
uv run expense-tracker
# Run in development mode with auto-reload
uv run python src/expense_tracker/server.py
# Install new dependencies
uv add package-name
# Update dependencies
uv sync
Project Structure
expense-tracker-mcp/
├── main.py # Main MCP server code
├── pyproject.toml # Project configuration
├── uv.lock # Locked dependencies
├── expenses.db # SQLite database (created on first run)
└── README.md
Use Cases
- Personal Finance Tracking: Monitor daily spending habits
- Budget Management: Track expenses by category to stay within budget
- Expense Reports: Generate summaries for tax purposes or reimbursements
- Shopping Tracking: Keep records of purchases and major expenses
- Financial Analysis: Analyze spending patterns over time
Built With
- fastmcp - Fast, Pythonic MCP server framework
- uv - Fast Python package installer and resolver
- SQLite - Lightweight database for expense storage
- Model Context Protocol - Protocol for AI-application integration
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Troubleshooting
Server not appearing in Claude Desktop?
- Ensure the path in
claude_desktop_config.jsonis absolute and correct - Restart Claude Desktop after configuration changes
- Check Claude Desktop logs for error messages
Database errors?
- Ensure the directory is writable
- Delete
expenses.dbto recreate the database from scratch
Support
If you encounter any issues or have questions, please open an issue on GitHub.
Made with ❤️ for better expense tracking through AI
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.