ExpenseTracker MCP Server

ExpenseTracker MCP Server

A lightweight server built with FastMCP and SQLite for managing personal finances. It allows users to add, list, and summarize expenses by category through MCP-compatible clients.

Category
访问服务器

README

💰 ExpenseTracker MCP Server

A lightweight and scalable Expense Tracking MCP Server built using FastMCP and SQLite. This server allows you to add, list, and summarize expenses efficiently, making it ideal for personal finance management or integration with MCP-compatible clients like Claude Desktop.


🚀 Features

  • ✅ Add expenses with category and notes
  • 📊 List expenses within a date range
  • 📈 Summarize expenses by category
  • 📂 Default categories support (with fallback)
  • ⚡ Async database operations using aiosqlite
  • ☁️ Cloud-ready (FastMCP deployment compatible)

🛠️ Tech Stack

  • Python
  • FastMCP
  • SQLite (aiosqlite for async support)

📁 Project Structure

.
├── main.py              # Main MCP server file
├── requirements.txt    # Dependencies
├── categories.json     # (Optional) Custom categories
└── README.md

⚙️ Setup & Installation

1. Clone the repository

git clone https://github.com/your-username/your-repo-name.git
cd your-repo-name

2. Create virtual environment

python -m venv venv
venv\Scripts\activate   # Windows

3. Install dependencies

pip install -r requirements.txt

▶️ Running the Server

python main.py

Server will start at:

http://0.0.0.0:8000

🌐 MCP Endpoint

Once deployed on FastMCP, your endpoint will look like:

https://your-app-name.fastmcp.app/mcp

⚠️ Note: Authentication is required to access this endpoint.


📌 Available Tools

➤ Add Expense

Adds a new expense entry.

Parameters:

  • date (YYYY-MM-DD)
  • amount (float)
  • category (string)
  • subcategory (optional)
  • note (optional)

➤ List Expenses

Fetch expenses within a date range.

Parameters:

  • start_date
  • end_date

➤ Summarize Expenses

Get category-wise expense summary.

Parameters:

  • start_date
  • end_date
  • category (optional)

📂 Categories Resource

Endpoint:

expense:///categories
  • Loads from categories.json if available
  • Falls back to default categories if file is missing

🧠 How It Works

  • Uses a temporary directory for database storage
  • Initializes database on startup
  • Uses async operations for better performance
  • Safe fallback mechanisms for missing files

⚠️ Common Issues & Fixes

❌ Pre-flight check failed

  • Ensure your file name is main.py
  • Make sure mcp = FastMCP(...) is correct
  • Check logs for missing dependencies

❌ Module not found

  • Add missing packages to requirements.txt

Example:

fastmcp
aiosqlite

💡 Future Improvements

  • User authentication system
  • Dashboard UI
  • Monthly budget tracking
  • Data export (CSV/Excel)

👨‍💻 Author

Built with ❤️ for learning and real-world MCP integration.


⭐ Support

If you like this project:

  • Star ⭐ the repo
  • Share with others
  • Contribute improvements

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选