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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。