mcp-expense-tracker
Enables tracking personal expenses by adding, listing, deleting, and summarizing expenses by day or month, stored locally in a JSON file.
README
mcp-expense-tracker
An MCP (Model Context Protocol) server for tracking expenses. Expenses are stored in a local JSON file, and the server exposes tools for adding expenses and summarizing totals by day or month.
Two equivalent implementations are included:
src/— TypeScript/Node, stdio transport. Use this with Claude Code or Claude Desktop.server.py— Python (FastMCP). Use this to deploy on FastMCP Cloud so it's reachable as a remote connector from claude.ai.
Tools
- add_expense — record an expense (
amount,category, optionaldescription, optionaldatedefaulting to today) - list_expenses — list expenses, optionally filtered by
start_date,end_date,category - delete_expense — delete an expense by
id - summarize — get the total (and per-category breakdown) for a
day,month, oralltime, anchored on an optionaldate
Deploy on FastMCP Cloud (for claude.ai)
FastMCP Cloud deploys directly from this GitHub repo. When it asks for an entrypoint, use:
server.py
(FastMCP Cloud auto-detects the mcp object in server.py; you'd only need server.py:mcp if the variable were named something else.) It installs requirements.txt automatically. Once deployed, add the resulting https://<your-app>.fastmcp.app/mcp URL as a custom connector in claude.ai's connector settings.
Storage caveat: server.py stores expenses in a local data/expenses.json file. Confirm your FastMCP Cloud plan gives that container a persistent disk — if storage is ephemeral/rebuilt on redeploy, expenses will reset. If you hit that, swap server.py's file-backed storage for a hosted database.
Node/TypeScript setup
npm install
npm run build
Run standalone
npm start
The server communicates over stdio, so it's meant to be launched by an MCP client rather than used directly in a terminal.
Use with Claude Code
claude mcp add expense-tracker -- node /absolute/path/to/mcp-tracker/build/index.js
Use with Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"expense-tracker": {
"command": "node",
"args": ["/absolute/path/to/mcp-tracker/build/index.js"]
}
}
}
Run the Python version locally
pip install -r requirements.txt
python server.py
Data storage
Expenses are stored in data/expenses.json (created automatically). Set EXPENSE_DATA_DIR to change where data is stored. This applies to both implementations.
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。