expense-tracker-mcp-server
Enables users to manage personal finances using natural language, including tracking expenses, income, budgets, and generating financial summaries.
README
Expense Tracker MCP Server 💰
This is a Model Context Protocol (MCP) server designed to connect with Claude Desktop and other MCP clients. It enables users to manage their personal finances using natural language.
🌟 The Vision
The ultimate goal of this project is to serve as the financial brain for an Integrated AI Agent (Personal Assistant). This assistant will utilize a small, high-performance local model designed to run efficiently on any device (mobile, laptop, or IoT), ensuring your financial data remains private, secure, and accessible offline.
🛠 Initial Tools (Available Now)
The server currently exposes the following capabilities to the AI:
- Add Expense: Record new spending with details including
amount,category,date, anddescription. - List Expenses: Retrieve records with the ability to filter by date range or category.
- Summarize Expenses: Generate a financial overview for any period, including total spending and a breakdown by category.
- Edit Expense: Modify details of an existing record (e.g., correcting an amount or updating a description).
- Delete Expense: Completely remove an entry from the records.
- Credit Expense (Income): Track money coming in to maintain a complete picture of cash flow.
🚀 Future Roadmap
These features are planned to transform the tracker into a proactive financial advisor:
- View Balance: Instant calculation of
Total Income - Total Expenses. - Create Budget: Set spending limits for specific categories and track progress.
- Alert Notifications: Proactive warnings when spending nears or exceeds budget limits.
- Export Data: Export your database to CSV or Excel for external bookkeeping.
- Visual Reports: Generation of charts and spending trend visualizations.
⚙️ Configuration
To use this with Claude Desktop, add the following to your claude_desktop_config.json:
{
"mcpServers": {
"ExpenseTracker": {
"command": "absolute path to uv",
"args": [
"run",
"--with",
"fastmcp",
"fastmcp",
"run",
"absolute path to main mcp file"
],
"env": {
"PATH": "Path to nodejs (Optional, if not already in system PATH)"
},
"transport": "stdio",
"type": null,
"cwd": null,
"timeout": null,
"description": null,
"icon": null,
"authentication": null
}
}
}
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。