Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Router list all connected MCP servers and their current health status"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A secure, enterprise-grade Model Context Protocol (MCP) server aggregation platform built with Electron.
MCP Router acts as a centralized gateway for managing multiple MCP servers, providing:
Server Aggregation: Connect and manage multiple MCP servers from a single interface
Policy-Based Access Control: Fine-grained control over tool and resource access
Token Authentication: Secure API token management with scoping and expiration
Approval Workflows: Human-in-the-loop approval for sensitive operations
Rate Limiting: Protect against abuse with configurable rate limits
Audit Logging: Complete audit trail of all operations
Related MCP server: MCP Gateway
┌─────────────────────────────────────────────────────────────────┐
│ MCP Router │
├─────────────────────────────────────────────────────────────────┤
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
│ │ Clients │ │ Policy │ │ Approval │ │
│ │ (Claude, │──│ Engine │──│ Queue │ │
│ │ etc.) │ │ │ │ │ │
│ └─────────────┘ └─────────────┘ └─────────────┘ │
│ │ │ │ │
│ ▼ ▼ ▼ │
│ ┌─────────────────────────────────────────────────────────┐ │
│ │ MCP Aggregator │ │
│ │ - Tool routing - Resource proxying - Audit log │ │
│ └─────────────────────────────────────────────────────────┘ │
│ │ │ │ │
│ ▼ ▼ ▼ │
│ ┌───────────┐ ┌───────────┐ ┌───────────┐ │
│ │ MCP Server│ │ MCP Server│ │ MCP Server│ │
│ │ A │ │ B │ │ C │ │
│ └───────────┘ └───────────┘ └───────────┘ │
└─────────────────────────────────────────────────────────────────┘Support for stdio and HTTP transport protocols
Automatic server health monitoring
Tool and resource discovery
Per-server configuration
Token-based authentication with scopes
Policy rules with glob pattern matching
Rate limiting per client/token
Secure credential storage via system keychain
Global, client-specific, and server-specific policies
Allow, deny, and require_approval actions
Priority-based rule evaluation
Wildcard pattern matching
Real-time approval notifications
Configurable timeout and expiration
Audit trail for all decisions
Node.js 20+
pnpm 9+
# Clone the repository
git clone https://github.com/your-org/mcp-router.git
cd mcp-router
# Install dependencies
pnpm install
# Start development server
pnpm dev# Build for production
pnpm build
# Package for distribution
pnpm packagemcp-router/
├── apps/
│ └── desktop/ # Electron desktop application
│ ├── src/
│ │ ├── main/ # Main process (Node.js)
│ │ │ ├── core/ # DI container, types, interfaces
│ │ │ ├── services/ # Business logic services
│ │ │ ├── repositories/ # Data access layer
│ │ │ └── ipc/ # IPC handlers
│ │ ├── preload/ # Preload scripts (context bridge)
│ │ └── renderer/ # React UI
│ │ ├── components/ # Reusable UI components
│ │ ├── features/ # Feature modules
│ │ ├── hooks/ # Custom React hooks
│ │ └── stores/ # Zustand state stores
│ └── tests/ # Test files
├── docs/ # Documentation
│ ├── adr/ # Architecture Decision Records
│ ├── api/ # API documentation
│ └── guides/ # User and developer guides
└── packages/ # Shared packages (future)Layer | Technology |
Framework | Electron 28 |
UI | React 18 + TypeScript |
Styling | Tailwind CSS + shadcn/ui |
State | Zustand |
DI | InversifyJS |
Database | SQLite (better-sqlite3) |
Build | electron-vite + Vite |
Testing | Vitest + Playwright |
Command | Description |
| Start development server |
| Build for production |
| Run unit tests |
| Run tests in watch mode |
| Run ESLint |
| Fix linting issues |
| Run TypeScript type checking |
Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request
MIT License - see LICENSE for details.
This server cannot be deployed
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
Governed MCP gateway: one endpoint for your tools, with credential custody and audit log.