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" } |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.