接入你的智能体
从发布者处安装。不是 PlugMCP 端点。
远程 URL 还是本机命令? 两种安装方式的区别
来自发布者
Secure middleware server implementing Model Context Protocol (MCP) over SSE with JWT authentication. Enables standardized communication between AI tools and clients with dynamic tool registration, request logging, and session management. Perfect for building production-ready AI systems requiring secure access patterns.
This is a Model Context Protocol (MCP) SSE server with JWT-based authentication.
It allows you to expose multiple AI tools over an SSE transport, protected via secure Bearer Token flow.
Built with:
✅ Fully tested with
@modelcontextprotocol/inspector
server/
├── index.ts # Main Express + MCP server
├── .env # Environment variables
├── package.json # Project metadata & scripts
├── tsconfig.json # TypeScript config
└── README.md # You are here!
git clone https://github.com/anisirji/mcp-server-remote-setup-with-jwt-auth.git
cd mcp-server-remote-setup-with-jwt-auth
npm install
.env fileecho "JWT_SECRET=your-secret-key" > .env
npm run dev
✅ Server will run on:
http://localhost:3001/sse
📖 Official Docs: MCP Inspector
npx @modelcontextprotocol/inspector
Use cURL to get your JWT token:
curl "http://localhost:3001/auth/token?username=aniket&scope=mcp:access"
✅ Example response:
{
"token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..."
}
http://localhost:3001/sse
Authorization: Bearer <your-token>
🎉 Success! Your server is now connected.
Go to Tools tab in Inspector and click List Tools.
You will see:
testechoget-timerandom-numberTest them and enjoy!
GET /auth/token?username=<username>&scope=mcp:access
GET /sse
Authorization: Bearer <token>
POST /message?sessionId=<sessionId>
Authorization: Bearer <token>
Aniket
This project is open-source and free to use.
Secure middleware server implementing Model Context Protocol (MCP) over SSE with JWT authentication. Enables standardized communication between AI tools and clients with dynamic tool registration, req
概览
Secure middleware server implementing Model Context Protocol (MCP) over SSE with JWT authentication. Enables standardized communication between AI tools and clients with dynamic tool registration, request logging, and session management. Perfect for building production-ready AI systems requiring secure access patterns.
工具
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
常见问题
在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
此记录未列出必需的环境变量。
MCP Server Remote Setup With Jwt Auth 通过 stdio 在本地运行。
上次检查时间:2026-10-27。 Secure middleware server implementing Model Context Protocol (MCP) over SSE with JWT authentication. Enables standardized communication between AI tools and clients with dynamic tool registration, request logging, and session management. Perfect for building production-ready AI systems requiring secure access patterns.