Expense Tracker MCP Server
Enables users to manage personal expenses through natural conversation with Claude, including adding, updating, deleting expenses, and viewing summaries by category or date range.
README
💰 Expense Tracker MCP Server
An intelligent expense tracking system built with the Model Context Protocol (MCP), allowing Claude AI to manage your personal finances through natural conversation.
🌟 Features
- User Management: Register and manage multiple users with phone numbers
- Expense Tracking: Add, update, and delete expenses with detailed metadata
- Smart Categorization: Organize expenses by categories and subcategories
- Date Range Queries: Filter expenses by custom date ranges
- Item Summaries: Get detailed breakdowns of spending by category
- Natural Language Interface: Interact with your expense data through Claude AI
🚀 What is MCP?
The Model Context Protocol (MCP) is an open standard by Anthropic that enables AI assistants like Claude to securely connect with external data sources and tools. This project implements an MCP server that gives Claude the ability to manage expense data in real-time.
🛠️ Tech Stack
- FastMCP: MCP server implementation
- PostgreSQL: Robust database for expense data
- SQLAlchemy: Async ORM for database operations
- Docker: Containerized PostgreSQL deployment
- Pydantic: Data validation
📋 Prerequisites
- Python 3.8+
- Docker and Docker Compose
- Claude Desktop App
🔧 Installation
1. Clone the Repository
git clone https://github.com/ArProvat/expense-tracker-mcp.git
cd expense-tracker-mcp
2. Install Dependencies
pip install -r requirements.txt
3. Start PostgreSQL Database
docker-compose up -d
This will start a PostgreSQL container with:
- Host: localhost
- Port: 5432
- Database: expenses
- User: postgres
- Password: postgres
4. Run Database Migrations
alembic upgrade head
5. Configure Claude Desktop
Add the MCP 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": "python",
"args": ["/path/to/your/expense-tracker-mcp/main.py"]
}
}
}
6. Restart Claude Desktop
Close and reopen Claude Desktop to load the MCP server.
📖 Usage
Once connected, you can interact with Claude naturally:
Register a User
"Register me as a user with phone number +1234567890"
Add Expenses
"Add an expense of $50 for groceries today"
"I spent 1500 taka on transportation yesterday"
View Expenses
"Show me all my expenses from last week"
"What did I spend in January 2025?"
Get Summaries
"Give me a summary of my food expenses this month"
"How much did I spend on entertainment?"
Update Expenses
"Update my last grocery expense to $45"
"Change the category of yesterday's expense to 'Shopping'"
Delete Expenses
"Delete my last expense"
"Remove the expense with ID abc123"
🎯 Available MCP Functions
Tool
add_user- Register a new useradd_expense- Add a new expense entryget_list_expenses- Retrieve expenses by date rangedelete_expense- Remove an expenseget_item_summary- Get spending summary by categoryupdate_expense- Modify existing expense details
Resource
categories.json-Define all categories and subcategories
📊 Database Schema
The system uses PostgreSQL to store:
- User profiles with contact information
- Expense records with amounts, categories, and dates
- Metadata for custom fields and tags
🤝 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.
🙏 Acknowledgments
- Anthropic for creating MCP and Claude
- FastMCP for the MCP server framework
- The open-source community for the amazing tools and libraries
📧 Contact
For questions or feedback, feel free to reach out or open an issue!
Built with ❤️ using Model Context Protocol
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。