expense-mcp
Personal expense tracker MCP server that enables tracking expenses, income, budgets, and savings goals through natural language.
README
💰 expense-mcp
Personal Expense Tracker as an MCP Server — works with Claude Desktop, Cursor, nanobot, Windsurf, and any MCP-compatible client.
<!-- mcp-name: io.github.justfsl50/expense-mcp -->
Features
- 📝 Track expenses & income with categories and descriptions
- 📊 Spending summaries — today, week, month, year
- 💳 Budget management — set limits per category, get alerts at 80%/100%
- 🎯 Savings goals — create goals, track progress with visual bars
- 📈 Spending insights — top categories, daily averages, biggest days
- 🗑️ Safe deletion — Pydantic-based elicitation for confirmation
- 🔄 Dual transport — stdio (local) + streamable HTTP (remote)
Install
# with uv (recommended)
uv pip install git+https://github.com/justfsl50/expense-mcp.git
# with pip
pip install git+https://github.com/justfsl50/expense-mcp.git
# from source
git clone https://github.com/justfsl50/expense-mcp.git
cd expense-mcp
pip install -e .
Quick Start
Claude Desktop
Add to %APPDATA%\Claude\claude_desktop_config.json (Windows) or ~/Library/Application Support/Claude/claude_desktop_config.json (Mac):
{
"mcpServers": {
"expense-mcp": {
"command": "uv",
"args": ["run", "expense-mcp"],
"env": {
"DATABASE_URL": "sqlite:///expenses.db",
"CURRENCY": "₹",
"DEFAULT_USER": "me"
}
}
}
}
Cursor / Windsurf
Same config — paste into MCP settings under the respective app.
nanobot
{
"mcp": {
"servers": [{
"name": "expense-mcp",
"command": "uv run expense-mcp"
}]
}
}
HTTP mode (remote / multi-client)
python server.py http
# Server runs at http://127.0.0.1:8000/mcp
Environment Variables
| Variable | Default | Description |
|---|---|---|
DATABASE_URL |
sqlite:///expenses.db |
SQLite or PostgreSQL URL |
CURRENCY |
₹ |
Currency symbol |
DEFAULT_USER |
default |
User ID for multi-user setups |
PostgreSQL example:
DATABASE_URL=postgresql://user:pass@localhost:5432/expenses
Tools
| Tool | Description | Read-only |
|---|---|---|
expense_add |
Save expense or income | ❌ |
expense_search |
Filter by text, date, category, amount | ✅ |
expense_summary |
today / week / month / year totals | ✅ |
expense_delete |
Delete with Pydantic confirmation prompt | ❌ |
expense_insights |
Spending patterns and top categories | ✅ |
budget_set |
Set monthly category budget | ❌ |
budget_list |
View budgets with usage % | ✅ |
goal_create |
Create savings goal | ❌ |
goal_update |
Add money toward goal | ❌ |
goal_list |
View goals with progress bars | ✅ |
Resources
| URI | Description |
|---|---|
expense://summary/month |
Current month summary |
expense://budgets/current |
This month's budgets |
expense://goals/all |
All savings goals |
Prompts
| Prompt | Title | Description |
|---|---|---|
monthly_review |
Monthly Review | Start a full month spending review |
budget_setup |
Budget Setup | Auto-suggest budgets from history |
savings_plan |
Savings Plan | Create a plan for a savings goal |
Usage Examples
Just talk naturally in any MCP client:
"spent 500 on groceries"
"show food expenses this week"
"how much did I spend last month?"
"set food budget to 5000"
"am I within budget?"
"save 1000 toward my iPhone goal"
"give me spending insights"
"delete expense #12"
Architecture
- MCP SDK v1.26.0 with
FastMCP+json_response=True - Typed lifespan — DB engine managed via
AppContextdataclass - SQLAlchemy 2.0 —
DeclarativeBase,sessionmaker - Pydantic v2 — input validation, elicitation schemas
- Tool annotations —
readOnlyHint,destructiveHint,idempotentHint - Context logging —
ctx.info(),ctx.warning()in tools
Database Schema
expenses — id, user_id, amount, category, description, type, date, source, created_at
budgets — id, user_id, category, amount, month
goals — id, user_id, name, target, saved, deadline
License
MIT — free to use, modify, and distribute.
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。