Financial MCP Server
Provides mock financial data including bank transactions, credit reports, and EPF details for the Finarrator application through authenticated API endpoints.
README
Financial MCP Server
Mock Financial Data MCP Server for Finarrator application.
Local Development
Setup
- Install dependencies:
npm install
- Set up environment variables in
.env:
PORT=10000
NODE_ENV=development
CREDENTIALS_FILE=./credentials.json
- Run the server:
npm run dev
The server will run on http://localhost:10000
Deployment on Render
Prerequisites
- Render account (render.com)
- GitHub repository with this code
Deployment Steps
-
Push to GitHub
- Ensure your MCP server code is in a GitHub repository
- Make sure
.gitignoreis properly configured
-
Connect to Render
- Go to render.com
- Click "New +" → "Web Service"
- Connect your GitHub repository
- Select the branch (usually
main)
-
Configure Settings
- Name:
financial-mcp-server - Environment:
Node - Build Command:
npm install - Start Command:
npm start - Plan: Free or Paid (based on your needs)
- Name:
-
Set Environment Variables In Render dashboard, add:
PORT:10000NODE_ENV:productionCREDENTIALS_FILE:./credentials.json
-
Deploy
- Click "Create Web Service"
- Render will automatically deploy on every push to your selected branch
Environment Variables for Production
Update these in Render dashboard:
PORT=10000
NODE_ENV=production
CREDENTIALS_FILE=./credentials.json
ALLOWED_ORIGINS=https://your-backend-domain.onrender.com,https://your-frontend-domain.vercel.app
API Endpoints
Health Check
GET /- Returns server status
Login
POST /api/login- Body:
{ mobile: string, password: string } - Returns: User financial data (bank transactions, credit report, EPF details, etc.)
- Body:
File Structure
.
├── server.js # Main server file
├── package.json # Dependencies and scripts
├── .env # Environment variables
├── .gitignore # Git ignore rules
├── credentials.json # User credentials (mock data)
├── render.yaml # Render deployment config
├── data/ # Mock financial data
│ ├── 1010101010/ # User directories
│ └── ...
└── views/ # EJS templates
Troubleshooting
Port Issues
- If port 10000 is already in use locally, change the PORT in
.env - Render automatically handles port assignment
Credentials Not Loading
- Ensure
credentials.jsonis in the root directory - Check that the path in
.envis correct
CORS Issues
- Update
ALLOWED_ORIGINSin environment variables - Restart the service after updating
Support
For issues or questions, check the main Finarrator documentation.
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。