MCP Gateway

MCP Gateway is a reverse proxy and management layer for Model Context Protocol (MCP) servers, enabling scalable, session-aware routing, authorization and lifecycle management of MCP servers in Kubernetes environments.

Table of Contents

• Overview
• Key Concepts
• Architecture
• Features
• Getting Started – Local Deployment
• Getting Started – 1-Click Deploy to Azure

Overview

This project provides:

• A data gateway for routing traffic to MCP servers with session affinity.
• A control plane for managing the MCP server lifecycle (deploy, update, delete).
• Enterprise-ready integration points including telemetry, access control and observability.

Key Concepts

• MCP Server: A server implementing the Model Context Protocol, which typically a streamable HTTP endpoint.
• Adapters: Logical resources representing MCP servers in the gateway, managed under the /adapters scope. Designed to coexist with other resource types (e.g., /agents) in a unified AI development platform.
• Tools: Registered resources with MCP tool definitions that can be dynamically routed via the tool gateway router. Each tool includes metadata about its execution endpoint and input schema.
• Tool Gateway Router: An MCP server that acts as an intelligent router, directing tool execution requests to the appropriate registered tool servers based on tool definitions. Multiple router instances may run behind the gateway for session affinity.
• Session-Aware Stateful Routing: Ensures that all requests with a given session_id are consistently routed to the same MCP server instance.
• Agents & Sessions (Preview): Optional, opt-in resources for running LLM-driven agents on top of registered MCP tools. Agents are metadata (system prompt + model + allowed tool list); Sessions are individual runs that stream events over Server-Sent Events. Disabled unless FoundrySettings:Endpoint is configured.

Architecture

flowchart LR
    subgraph Clients[" "]
        direction TB
        DataClient["🔌 Agent/MCP<br>Data Client"]
        MgmtClient["⚙️ Management<br>Client"]
    end

    subgraph Gateway["MCP Gateway"]
        direction TB
        
        subgraph Auth1["Authentication & Authorization"]
            Auth["🔐 Data Plane Auth<br>Bearer Token / RBAC"]
            Auth2["🔐 Control Plane Auth<br>Bearer Token / RBAC"]
        end
        
        subgraph DataPlane["Data Plane"]
            Routing["🔀 Adapter Routing<br>/adapters/{name}/mcp"]
            ToolRouting["🔀 Tool Router Gateway<br>/mcp"]
        end

        subgraph ControlPlane["Control Plane"]
            direction LR
            AdapterMgmt["📦 Adapter Management<br>/adapters CRUD"]
            ToolMgmt["🔧 Tool Management<br>/tools CRUD"]
        end
        
        subgraph Management["Backend Services"]
            DeploymentMgmt["☸️ Deployment Manager"]
            MetadataMgmt["📋 Metadata Manager"]
        end
    end

    subgraph Cluster["Kubernetes Cluster"]
        direction TB
        
        subgraph ServerRow[" "]
            direction LR
            
            subgraph MCPServers["MCP Servers"]
                direction TB
                PodA["mcp-a-0"]
                PodA1["mcp-a-1"]
                PodB["mcp-b-0"]
            end
            
            subgraph ToolRouters["Tool Gateway Routers"]
                direction TB
                Router1["toolgateway-0"]
                Router2["toolgateway-1"]
            end
        end
        
        subgraph ToolServers["Registered Tool Servers"]
            direction LR
            Tool1["tool-1-0"]
            Tool2["tool-2-0"]
        end
    end

    Metadata[("💾 Metadata Store<br>Server & Tool Info")]

    DataClient -->|"MCP Requests"| Auth
    MgmtClient -->|"API Calls"| Auth2
    
    Auth --> Routing
    Auth --> ToolRouting
    Auth2 --> AdapterMgmt
    Auth2 --> ToolMgmt
    
    AdapterMgmt & ToolMgmt --> DeploymentMgmt
    AdapterMgmt & ToolMgmt --> MetadataMgmt
    
    Routing -.->|"Session Affinity"| MCPServers
    ToolRouting -.->|"Session Affinity"| ToolRouters
    ToolRouters ==>|"Dynamic Routing"| ToolServers
    
    DeploymentMgmt -->|"Deploy & Monitor"| Cluster
    MetadataMgmt <-->|"Read/Write"| Metadata

    style Gateway fill:#e1f5ff
    style Cluster fill:#fff4e1
    style Metadata fill:#f0f0f0

Features

Control Plane – RESTful APIs for MCP Server Management

MCP Server Management (Adapters)

• POST /adapters — Deploy and register a new MCP server.
• GET /adapters — List all MCP servers the user can access.
• GET /adapters/{name} — Retrieve metadata for a specific adapter.
• GET /adapters/{name}/status — Check the deployment status.
• GET /adapters/{name}/logs — Access the server's running logs.
• PUT /adapters/{name} — Update the deployment.
• DELETE /adapters/{name} — Remove the server.

Tool Registration and Management

• POST /tools — Register and deploy a tool with MCP tool definition metadata.
• GET /tools — List all registered tools the user can access.
• GET /tools/{name} — Retrieve metadata and tool definition for a specific tool.
• GET /tools/{name}/status — Check the tool deployment status.
• GET /tools/{name}/logs — Access the tool server's running logs.
• PUT /tools/{name} — Update a tool deployment and definition.
• DELETE /tools/{name} — Remove a registered tool.

Agent and Session Management (Preview, opt-in)

Available only when FoundrySettings:Endpoint is configured. See Agents and Sessions below for details.

• POST /agents, GET /agents, GET|PUT|DELETE /agents/{name} — CRUD for agent definitions.
• POST /sessions, GET /sessions, GET|DELETE /sessions/{id} — CRUD for sessions.
• POST /sessions/run — Start a session and stream events (SSE).
• POST /sessions/{id}/messages — Continue an existing session with a new user message; streams events (SSE).

Data Plane – Gateway Routing for MCP Servers

Direct MCP Server Access

• POST /adapters/{name}/mcp — Establish a streamable HTTP connection.

Dynamic Tool Routing via Tool Gateway Router

• POST /mcp — Route requests to the tool gateway router, which dynamically routes to registered tools based on tool definitions. The router itself is an MCP server with multiple instances hosted behind the gateway for scalability.

Authentication & Authorization Support

The gateway provides entra id authentication and basic application role authorization for mcp servers and tools:

• Read access is granted to the resource creator, principals assigned the configured requiredRoles values (for example mcp.engineer), and anyone holding the mandatory administrator role mcp.admin. When requiredRoles is empty or omitted, only the creator and mcp.admin principals can read the resource.
• Write access is restricted to the resource creator or principals holding the mcp.admin role.

For step-by-step guidance on configuring Azure Entra ID (creating mcp.admin and other role values, assigning them to users or service principals, and supplying those values in adapter/tool payloads), see docs/entra-app-roles.md.

Additional Capabilities

• Support for Proxying Local & Remote MCP Servers. See examples and usage.
• Stateless reverse proxy with a distributed session store (production mode).
• Kubernetes-native deployment using StatefulSets and headless services.
• Management portal (React SPA) served by the gateway itself at /portal/ — list / create / edit / delete adapters and tools, inspect status and pod logs, and exercise each MCP server with an in-browser JSON-RPC test console. Authentication mirrors the API: anonymous in dev mode (with an optional dev-identity switcher) and MSAL / Entra ID in cloud mode, so every list call already filters down to the resources the signed-in user is allowed to see.

Tool Registration and Dynamic Routing

The MCP Gateway now supports tool registration with dynamic routing capabilities, enabling a scalable architecture for managing and executing MCP tools.

How It Works

1. Tool Registration: Developers register tools via the /tools API endpoint, providing:

   • Container image details (name and version)
   • MCP tool definition (name, description, input schema)
   • Execution endpoint configuration (port and path)
   • Deployment configuration (replicas, environment variables)

2. Tool Gateway Router: A specialized MCP server that acts as an intelligent router:

   • Runs as multiple instances behind the gateway for high availability
   • Maintains awareness of all registered tools and their definitions