Expense Tracker MCP Server
Enables users to track expenses by adding, listing, and summarizing them with category support through natural language.
README
Expense Tracker MCP Server
A simple Expense Tracker MCP server built with FastMCP and SQLite, deployed on FastMCP Cloud.
This project demonstrates how to build, deploy, and connect an MCP server using FastMCP Cloud and Claude Desktop.
Features
Tools
- add_expense — Add a new expense.
- list_expenses — View expenses within a date range.
- summarize — Generate expense summaries by category.
Resources
- expense:///categories — Returns available expense categories and subcategories.
Tech Stack
- Python 3.14+
- FastMCP 3.4.0
- SQLite
- aiosqlite
- FastMCP Cloud
Local Development
Run the server locally:
uv run python main.py
Open MCP Inspector:
uv run fastmcp dev inspector main.py
Deployment
This project is deployed to FastMCP Cloud.
Remote MCP Endpoint (example url):
https://splendid-gold-dingo.fastmcp.app/mcp
Claude Desktop Integration
Create a local proxy server:
from fastmcp import FastMCP
mcp = FastMCP.as_proxy(
"https://splendid-gold-dingo.fastmcp.app/mcp", # example url, get your url from fastmcp cloud
name="Neel Server Proxy"
)
if __name__ == "__main__":
mcp.run()
Install the proxy into Claude Desktop:
uv run fastmcp install claude-desktop proxy.py
Restart Claude Desktop after installation.
Example Prompts
Add an expense:
Add an expense for a cab ride to Delhi last Sunday. The fare was ₹600.
List expenses:
Show all expenses between 2026-06-01 and 2026-06-30.
Summarize expenses:
Summarize my expenses for June 2026.
Categories
The server supports categories such as:
- Food
- Transport
- Housing
- Utilities
- Health
- Education
- Entertainment
- Shopping
- Travel
- Business
- Investments
- Personal Care
- Taxes
- Miscellaneous
Learning Goal
This project was created to learn:
- FastMCP fundamentals
- MCP tools and resources
- SQLite integration
- Async MCP tools with aiosqlite
- FastMCP Cloud deployment
- Claude Desktop integration via MCP
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。