Finance MCP Server
Enables financial management through MCP tools for account viewing, transaction analysis, budgeting, and analytics, deployable on Vercel.
README
Finance MCP Server - Vercel Deployment
This folder contains the Finance MCP Server configured for serverless deployment on Vercel.
📁 Structure
vercel-deployment/
├── api/
│ ├── index.py # Main Vercel handler
│ ├── app_tools.py # MCP tools registration
│ └── database.py # Database connection manager
├── vercel.json # Vercel configuration
├── requirements.txt # Python dependencies
├── .env.example # Environment variables template
└── README.md # This file
🚀 Quick Deployment
1. Install Vercel CLI
npm install -g vercel
2. Set Environment Variables
Create a .env file (copy from .env.example):
DATABASE_URL_PRIVATE="postgresql://user:pass@host/private?sslmode=require"
DATABASE_URL_PUBLIC="postgresql://user:pass@host/public?sslmode=require"
3. Deploy to Vercel
cd vercel-deployment
vercel
Follow the prompts:
- Set up and deploy? Y
- Which scope? Select your account
- Link to existing project? N (for first deployment)
- What's your project's name? finance-mcp-server
- In which directory is your code located? ./
- Want to override settings? N
4. Add Environment Variables to Vercel
After deployment, add your secrets:
# Add private database URL
vercel env add DATABASE_URL_PRIVATE
# Add public database URL
vercel env add DATABASE_URL_PUBLIC
Or add them via Vercel Dashboard:
- Go to your project settings
- Navigate to "Environment Variables"
- Add
DATABASE_URL_PRIVATEandDATABASE_URL_PUBLIC - Redeploy:
vercel --prod
🔧 Configuration
vercel.json
The vercel.json file configures:
- Python runtime for serverless functions
- Routing to handle MCP endpoints
- Environment variables references
Production Deployment
vercel --prod
Your MCP server will be available at:
https://your-project.vercel.app/mcp
📡 API Endpoints
Once deployed, your MCP server will be accessible at:
- Main MCP endpoint:
https://your-project.vercel.app/mcp - Health check:
https://your-project.vercel.app/
🔐 Security
- Never commit
.envfile - it's already in.gitignore - Use Vercel environment variables for production secrets
- Enable SSL - Vercel provides automatic HTTPS
- Database SSL - Ensure Neon databases use
?sslmode=require
🧪 Testing
Local Testing
# Install dependencies
pip install -r requirements.txt
# Run locally
python api/index.py
Server runs at http://localhost:8080
Test MCP Endpoint
curl https://your-project.vercel.app/mcp
📊 Features
All 19 financial tools are available:
Account Management
list_accounts- View all accountsget_account_balance- Get specific account balanceget_account_summary- Complete financial summary
Transaction Analysis
list_transactions- List with filterssearch_transactions- Search by merchantget_recurring_transactions- Detect recurring payments
Analytics
get_spending_by_category- Category breakdownget_monthly_trends- Income/expense trendsget_top_merchants- Top spending merchantsget_cashflow_summary- Income vs expenses
Budgeting
create_budget- Create new budgetlist_budgets- View all budgetsget_budget_status- Budget vs actual spending
Utilities
get_available_categories- List categoriesformat_currency- Format amountscalculate_net_worth- Calculate net worth
Security & Policies
get_tool_policy- Get tool access policylist_tool_policies- List all policiesvalidate_tool_access- Validate permissions
🔄 Updates
To update the deployment:
# Pull latest changes
git pull
# Navigate to vercel-deployment folder
cd vercel-deployment
# Redeploy
vercel --prod
📝 Logs
View logs in real-time:
vercel logs
Or view in Vercel Dashboard under your project's "Logs" section.
🐛 Troubleshooting
Import Errors
Make sure all Python files are in the api/ directory and dependencies are in requirements.txt.
Database Connection Issues
- Verify environment variables are set correctly in Vercel
- Check database URLs include
?sslmode=require - Ensure Neon databases are accessible
500 Server Errors
Check Vercel logs: vercel logs or in the dashboard
📚 Resources
📞 Support
For issues or questions:
- Check Vercel logs
- Review environment variables
- Test database connections
- Verify Python dependencies
Ready to deploy! 🚀
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。