expense-tracker-mcp-server
A cloud-deployed MCP server for managing personal expenses and providing financial analytics. It enables AI assistants like Claude Desktop to add, update, delete, and retrieve expenses, with features like budgeting assistance and category-wise summaries.
README
Expense Tracker MCP Server
This project is a cloud-deployed Model Context Protocol (MCP) server for managing personal expenses and providing financial analytics. It exposes standardized MCP Tools, Resources, and Prompts, enabling AI assistants like Claude Desktop to interact with the expense tracker.
Features
- Add, update, delete, and retrieve expenses
- Financial analytics (summary, category-wise, monthly, daily average)
- Budgeting assistant through MCP Prompts
- MCP Resources for application metadata
- Tested with Claude Desktop and MCP Inspector
- Deployed on FastMCP Cloud
Tech Stack
- Language: Python
- Protocol: Model Context Protocol (MCP)
- Framework: FastMCP
- Data Validation: Pydantic
- Database: SQLite
- AI Client: Claude Desktop
- Testing: MCP Inspector
- Deployment: FastMCP Cloud
Live Deployment
Endpoint
https://mcp-server-expense-tracker.fastmcp.app/mcp
Protected by Horizon authentication.
Local Setup
If remote access is unavailable (e.g., due to FastMCP Cloud free-plan authentication), the server can be run locally and connected to Claude Desktop or MCP Inspector.
Clone the repository
git clone https://github.com/shubhangi115/expense-tracker-mcp-server.git
cd expense-tracker-mcp-server
Create and activate a virtual environment
python -m venv .venv
Windows
.venv\Scripts\activate
macOS / Linux
source .venv/bin/activate
Install dependencies
pip install -r requirements.txt
Run the MCP server
fastmcp run main.py
Connect with Claude Desktop
Add the following configuration to your claude_desktop_config.json:
{
"mcpServers": {
"Expense Tracker": {
"command": "C:\\path\\to\\expense-tracker-mcp-server\\.venv\\Scripts\\fastmcp.exe",
"args": [
"run",
"C:\\path\\to\\expense-tracker-mcp-server\\main.py"
],
"transport": "stdio"
}
}
}
Replace:
C:\path\to\expense-tracker-mcp-server
with the path where you cloned the repository.
Test with MCP Inspector
npx @modelcontextprotocol/inspector
Configure:
Transport: STDIO
Command: fastmcp
Arguments: run main.py
Note: Running the server locally provides full functionality with Claude Desktop and MCP Inspector.
Setup Instructions
git clone https://github.com/shubhangi115/expense-tracker-mcp-server.git
cd expense-tracker-mcp-server
python -m venv .venv
.venv\Scripts\activate
pip install -r requirements.txt
fastmcp run main.py
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。