Expense Tracker MCP Server
A Model Context Protocol (MCP) server for tracking personal expenses. This server provides tools to add, list, and summarize expenses, utilizing a local SQLite database for storage.
README
Expense Tracker MCP Server
A Model Context Protocol (MCP) server for tracking personal expenses. This server provides tools to add, list, and summarize expenses, utilizing a local SQLite database for storage.
Features
- Add Expenses: Log expenses with details including amount, category, subcategory, date, and notes.
- List Expenses: Retrieve a list of expenses within a specified date range.
- Summarize Expenses: Generate summaries of expenses (total amount) grouped by category.
- Categories Resource: Access a comprehensive list of predefined expense categories.
- Local Database: All data is stored in a local
expenses.dbfile.
Prerequisites
Installation
-
Clone the repository (if applicable) or navigate to the project directory:
cd "d:\Study\Expense Tracker MCP" -
Install dependencies:
Using
uv:uv syncOr using
pip:pip install -e .
Usage
Running Locally
You can run the MCP server locally for testing or development.
Development mode (with auto-reload):
uv run fastmcp dev main.py
Production run:
uv run fastmcp run main.py
Inspector
You can inspect and test the server tools using the MCP Inspector:
uv run fastmcp inspect main.py
Integration with Claude Desktop
To use this Expense Tracker with Claude Desktop:
-
Open your Claude Desktop configuration file:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
-
Add the
expense-trackerserver to themcpServersobject. Make sure to use the absolute path to yourmain.pyfile.{ "mcpServers": { "expense-tracker": { "command": "uv", "args": [ "run", "fastmcp", "run", "d:/Study/Expense Tracker MCP/main.py" ] } } } -
Restart Claude Desktop.
Tools Available
add_expense
Adds a new expense entry.
- Arguments:
amount(float): The cost of the expense.category(string): The category of the expense (seecategoriesresource).subcategory(string, optional): A more specific classification.note(string, optional): Additional details.date(string, optional): Date of expense inDD-MM-YYYYformat. Defaults to current date (IST) if omitted.
list_expenses
Lists expenses within a date range.
- Arguments:
start_date(string): Start date inDD-MM-YYYYformat.end_date(string): End date inDD-MM-YYYYformat.
summarize
Summarizes expenses by category.
- Arguments:
start_date(string): Start date inDD-MM-YYYYformat.end_date(string): End date inDD-MM-YYYYformat.category(string, optional): Filter by a specific category.
Resources
expense://categories
Returns the JSON content of the available expense categories.
Project Structure
main.py: The core MCP server implementation.expenses.db: SQLite database file (created automatically).categories.json: specific categories configuration.pyproject.toml: Project configuration and dependencies.
Notes
- Date Format: The system uses
DD-MM-YYYYfor date storage and querying. - Timezone: Default dates are calculated in Indian Standard Time (IST).
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。