Expense Tracker MCP Server
Enables personal expense management with SQLite storage, allowing users to add, update, delete, list, and summarize expenses by category through natural language interactions.
README
Expense Tracker MCP Server
A Model Context Protocol (MCP) server for tracking personal expenses with SQLite database storage. This server integrates with Claude Desktop to provide expense management capabilities through natural language.
Features
- ✅ Add, update, and delete expenses
- ✅ List expenses by date range
- ✅ Summarize expenses by category
- ✅ Flexible deletion by multiple criteria
- ✅ Predefined expense categories
- ✅ SQLite database for persistent storage
Prerequisites
- Python 3.10 or higher
- uv package manager
- Claude Desktop app
Installation
1. Install uv
Windows (PowerShell):
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
macOS/Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
2. Initialize Project
# Create and navigate to project directory
mkdir expense-tracker-mcp-server
cd expense-tracker-mcp-server
# Initialize uv project
uv init .
3. Install Dependencies
# Install required packages
uv add fastmcp
uv add sqlite3 # Usually comes with Python
4. Create the Server
Create a file named main.py and paste the expense tracker code (from the document provided).
5. Test the Server
# Run the server
uv run main.py
Configuration
Claude Desktop Setup
-
Open Claude Desktop configuration file:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
- Windows:
-
Add the MCP server configuration:
{
"mcpServers": {
"expense-tracker": {
"command": "uv",
"args": [
"--directory",
"C:/Users/YOUR_USERNAME/Desktop/expense-tracker-mcp-server",
"run",
"main.py"
]
}
}
}
Important: Replace C:/Users/YOUR_USERNAME/Desktop/expense-tracker-mcp-server with your actual project path.
- Restart Claude Desktop
Usage
Once configured, you can interact with the expense tracker through Claude using natural language:
Add Expense
"Add an expense: $50 for groceries on 2024-12-14"
"Log $25.50 spent on transport today with note 'Uber to office'"
List Expenses
"Show me all expenses from December 1 to December 14, 2024"
"List my expenses for last week"
Update Expense
"Update expense ID 5 to $75"
"Change the category of expense 3 to 'entertainment'"
Delete Expense
"Delete expense with ID 5"
"Remove all food expenses from last week"
"Delete expenses in the transport category"
Summarize Expenses
"Summarize my expenses by category for December 2024"
"What's my total spending on food this month?"
View Categories
"What expense categories are available?"
"Show me the list of categories"
Available Tools
add_expense
Add a new expense to the tracker.
Parameters:
date(string): Date in YYYY-MM-DD formatamount(float): Expense amountcategory(string): Expense categorysubcategory(string, optional): Subcategorynote(string, optional): Additional notes
list_expenses
List all expenses within a date range.
Parameters:
start_date(string): Start date (YYYY-MM-DD)end_date(string): End date (YYYY-MM-DD)
update
Update an existing expense (only provided fields will be updated).
Parameters:
cid(int): Expense ID to updatedate(string, optional): New dateamount(float, optional): New amountcategory(string, optional): New categorysubcategory(string, optional): New subcategorynote(string, optional): New note
delete
Delete expenses based on various criteria.
Parameters:
id(int, optional): Delete by IDdate(string, optional): Delete by datecategory(string, optional): Delete by categorysubcategory(string, optional): Delete by subcategoryamount(float, optional): Delete by amountnote(string, optional): Delete by notestart_date&end_date(strings, optional): Delete by date range
summarize
Get expense summaries grouped by category.
Parameters:
start_date(string): Start date (YYYY-MM-DD)end_date(string): End date (YYYY-MM-DD)category(string, optional): Filter by specific category
Available Resources
expense://categories
Returns the list of available expense categories in JSON format.
Database Schema
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 ''
);
File Structure
expense-tracker-mcp-server/
├── main.py # MCP server code
├── expense.db # SQLite database (auto-created)
├── categories.json # Categories list (auto-created)
├── pyproject.toml # uv project configuration
└── README.md # This file
Default Categories
The server comes with these default categories:
- food
- transport
- entertainment
- utilities
- healthcare
You can modify categories.json to add or remove categories.
Troubleshooting
Server not appearing in Claude Desktop
- Check the configuration file path is correct
- Ensure the
commandpath points to your project directory - Restart Claude Desktop completely
- Check Claude Desktop logs for errors
Database errors
If you encounter database errors:
# Delete the database to reset
rm expense.db
# Restart the server to recreate the database
uv run main.py
Import errors
# Reinstall dependencies
uv sync
Development
To modify the server:
- Edit
main.py - Test changes:
uv run main.py - Restart Claude Desktop to load changes
Contributing
Contributions are welcome! Feel free to submit issues or pull requests.
Support
For issues related to:
- MCP Protocol: MCP Documentation
- FastMCP: FastMCP GitHub
- Claude Desktop: Anthropic 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。