Expense Tracker MCP
Enables management of expenses via SQLite database, including adding, listing, updating, deleting, filtering, and summing expenses through natural language.
README
💰 Expense Tracker MCP + Google ADK Agent
This project connects a Google ADK Agent with a FastMCP server --> local to manage an SQLite-based Expense Tracker.
The agent can:
- ➕ Add expense
- 📋 List expenses
- ✏️ Update expense
- ❌ Delete expense
- 📊 Sum expenses
- 🗂 Filter by category
- 📅 Filter by date range
- 🤖 Execute dynamic queries
- 🎲 Auto-generate multiple expenses
🏗 Project Structure
⚙️ Requirements
- Python 3.10+
- pip or uv
- Virtual environment (recommended)
- Groq or OpenAI API Key
🚀 Setup Instructions
1️⃣ Clone the Repository
cd Expense-tracker-MCP
2️⃣ create vertual Environment
python -m venv .venv
3️⃣ Activate Virtual Environment
.venv\Scripts\activate
4️⃣ Install Dependencies
pip install fastmcp google-adk litellm groq python-dotenv fastmcp
5️⃣ Run the ADK Agent
adk run my_agent
pip install fastmcp psutil platformdirs psutil system information ke liye use hoga.
🖥️ FastMCP System Monitor
A FastMCP server tool to monitor your system information. You can fetch battery, RAM, CPU, disk, and OS info remotely via an MCP client like Claude Desktop.
🚀 Features
- Get Battery status (percentage & charging).
- Get RAM usage (total, used, percentage).
- Get Disk usage (total, used, free space).
- Get CPU usage (percentage).
- Get System info (OS, hostname, processor).
- Accessible via HTTP MCP server, compatible with Claude Desktop or other MCP clients.
📦 Requirements
- Python 3.10+
- Libraries:
pip install fastmcp psutil platformdirs
📄 Installation
- Clone or download this repository.
- Ensure Python and required libraries are installed.
- Place the file
system_mcp_server.pyin a suitable location.
⚙️ Usage
1. Run the MCP server
cd expense-tracker-mcp
uv run laptop_status.py
- By default, the server starts on HTTP port 8004.
- You can change the port in the
main()function:
mcp.run(transport="http", port=YOUR_PORT)
2. Using with Claude Desktop
- Open Claude Desktop.
- Add the MCP server in the config file:
{
"mcpServers": {
"proxy": {
"command": "uv",
"args": [
"run",
"--with",
"fastmcp",
"fastmcp",
"run",
"C:\\Users\\MM0956\\Documents\\Expense-tracker-MCP\\proxy.py"
],
"env": {},
"transport": "stdio",
"type": null,
"cwd": null,
"timeout": null,
"description": null,
"icon": null,
"authentication": null
}
}
}
or you can run this command to add this configuration directly by vscode terminal
cd expense-tracker-mcp
uv run fastmcp install claude-desktop .\proxy.py
- Restart Claude Desktop.
- Query your system using natural language:
- "Check my battery"
- "What is my RAM usage?"
- "Show disk space"
- "Show CPU usage"
- "Give me system info"
🛠️ Tools / Endpoints
| Tool Name | Description | Example Output |
|---|---|---|
get_battery |
Returns battery percentage & charging status | { "percent": 87, "charging": true } |
get_ram |
Returns RAM total, used, and percent used | { "total_gb": 16, "used_gb": 8.5, "percent_used": 53.1 } |
get_disk |
Returns disk usage (total, used, free) | { "total_gb": 512, "used_gb": 256, "free_gb": 256 } |
get_cpu |
Returns CPU usage percentage | { "cpu_percent": 25.3 } |
get_system_info |
Returns OS, hostname, processor info | { "system": "Windows", "node": "DESKTOP-123", "release": "10", "processor": "Intel i7-9750H" } |
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。