Expense Tracker MCP Server
Enables users to manage personal expenses, analyze spending patterns, track budgets, generate reports, and export data through natural language conversations with Claude.
README
Expense Tracker MCP Server
An AI-powered Expense Tracker built using FastMCP, SQLite, and Claude Desktop.
This MCP (Model Context Protocol) server enables Claude to manage personal expenses, analyze spending patterns, track budgets, generate reports, and export data through natural language conversations.
Features
Expense Management
- Add expenses
- Update expenses
- Delete expenses
- Search expenses
- List expenses by date range
Analytics
- Monthly spending reports
- Category-wise spending summaries
- Spending insights
- Largest transactions analysis
- Top spending categories
Budget Management
- Set monthly budgets
- Track budget utilization
- Monitor remaining budget
Export
- Export expenses to CSV
AI Integration
Works with Claude Desktop through MCP.
Example queries:
- "Add ₹250 for lunch today."
- "Show my expenses for June."
- "What was my highest spending category this month?"
- "Have I exceeded my food budget?"
- "Export all expenses from May."
Tech Stack
- Python 3.11+
- FastMCP
- SQLite
- Claude Desktop
- JSON
Project Structure
expense-tracker-mcp-server/
│
├── main.py
├── expenses.db
├── categories.json
├── exports/
│ └── *.csv
├── pyproject.toml
└── README.md
Database Schema
Expenses Table
CREATE TABLE expenses(
id INTEGER PRIMARY KEY AUTOINCREMENT,
date TEXT NOT NULL,
amount REAL NOT NULL,
category TEXT NOT NULL,
subcategory TEXT DEFAULT '',
note TEXT DEFAULT ''
);
Budgets Table
CREATE TABLE budgets(
id INTEGER PRIMARY KEY AUTOINCREMENT,
category TEXT UNIQUE NOT NULL,
monthly_limit REAL NOT NULL
);
Installation
Clone Repository
git clone https://github.com/your-username/expense-tracker-mcp-server.git
cd expense-tracker-mcp-server
Create Virtual Environment
Windows:
python -m venv mcp_venv
mcp_venv\Scripts\activate
Linux / macOS:
python -m venv mcp_venv
source mcp_venv/bin/activate
Install Dependencies
pip install -r requirements.txt
or
pip install fastmcp
Running the MCP Server
python main.py
MCP Tools
| Tool | Description |
|---|---|
| add_expense | Add a new expense |
| list_expenses | View expenses within a date range |
| update_expense | Modify an existing expense |
| delete_expense | Remove an expense |
| search_expenses | Search expenses by keyword |
| summarize | Category-wise spending summary |
| monthly_report | Monthly spending statistics |
| spending_insights | Advanced spending analysis |
| set_budget | Create or update a budget |
| get_budget_status | Track budget utilization |
| export_csv | Export expenses to CSV |
Claude Desktop Integration
Add the following configuration to Claude Desktop:
{
"mcpServers": {
"expense-tracker": {
"command": "python",
"args": [
"C:\\path\\to\\expense-tracker-mcp-server\\main.py"
]
}
}
}
Restart Claude Desktop after updating the configuration.
Example Prompts
Add Expense
Add ₹500 for groceries today.
Get Spending Insights
Give me spending insights for 2026-06.
Budget Tracking
Set my food budget to ₹10000.
How much budget is remaining for food this month?
Export Data
Export all expenses from June 2026.
Future Improvements
- Income tracking
- Recurring expenses
- Expense forecasting
- AI-generated financial recommendations
- Category trend analysis
- Monthly comparison reports
- Dashboard integration
- Multi-user support
- PostgreSQL support
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。