Anisirji MCP Server Remote Setup With Jwt Auth

🚀 SSE MCP Server with JWT Authentication

This is a Model Context Protocol (MCP) SSE server that supports JWT authentication, allowing multiple AI tools to be exposed through a secure Bearer token stream.

Technologies used:

• 🚀 Node.js + Express
• 🧩 @modelcontextprotocol/sdk
• 🔒 JSON Web Tokens (JWT) for authentication
• ⚙️ Zod for input validation

✅ Fully tested with @modelcontextprotocol/inspector

📂 Project Structure

server/
├── index.ts          # Main Express + MCP server
├── .env              # Environment variable file
├── package.json      # Project metadata and scripts
├── tsconfig.json     # TypeScript configuration
└── README.md         # You are here!

✨ Features

• ✅ Secure SSE connections using Bearer JWT tokens
• ✅ Dynamic tool registration (Echo, Time, Random Number, etc.)
• ✅ Tested with MCP Inspector
• ✅ Log all request lifecycle events
• ✅ Session management at the /message endpoint
• 🚀 Ready to scale to production

⚙️ Project Setup

1. Clone the repository

git clone https://github.com/anisirji/mcp-server-remote-setup-with-jwt-auth.git
cd mcp-server-remote-setup-with-jwt-auth

2. Install dependencies

npm install

3. Create the .env file

echo "JWT_SECRET=your-secret-key" > .env

4. Run the server

npm run dev

✅ The server will run at the following address:

http://localhost:3001/sse

🧪 Testing the Server with MCP Inspector

Step 1 — Install MCP Inspector

📖 Official documentation: MCP Inspector

npx @modelcontextprotocol/inspector

Step 2 — Generate a token

Use cURL to get your JWT token:

curl "http://localhost:3001/auth/token?username=aniket&scope=mcp:access"

✅ Example response:

{
  "token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..."
}

Step 3 — Connect MCP Inspector

1. Open the Inspector UI
2. Set up the SSE connection
3. Add the following header:
   • Authorization: Bearer
4. Click "Connect"

Now you can start testing various tools!

📦 API Reference

Generate a token

• Request method: GET
• Path: /auth/token
• Parameters:
  • username: Username
  • scope: Permission scope (e.g., mcp:access)
• Response:

  {
    "token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..."
  }
  

SSE connection

• Request method: GET
• Path: /sse

Send a message to a session

• Request method: POST
• Path: /message/{sessionId}
• Body content:

  {
    "text": "Message text"
  }
  

💻 Usage Examples

Basic Usage

Echo Tool

app.use('/echo', (req, res) => {
  res.send({ echo: req.query.text });
});

Time Tool

app.use('/time', (req, res) => {
  res.send({ time: new Date().toISOString() });
});

🌟 Future Plans

• Token revoke list: Support token revocation functionality
• Role-based access control (RBAC): Enhance security
• Tool discovery mechanism: Automatically discover available tools
• Logging and monitoring: Add logging and performance monitoring

This project provides a solid foundation for building a secure and scalable AI tool platform. Although some additional features may be needed for perfection, the existing structure and documentation are already very clear.