MCP.so
ログイン

Model Context Protocol (MCP) Server

@adrianozagallo-home

Model Context Protocol (MCP) Server について

mcp-server

基本情報

カテゴリ

その他

ランタイム

node

トランスポート

stdio

公開者

adrianozagallo-home

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-server-adrianozagallo-home": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "mcp-server:latest",
        "."
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Model Context Protocol (MCP) Server?

The Model Context Protocol (MCP) Server is a Node.js application deployed on Azure Kubernetes Service (AKS) that exposes an HTTP API with health checks, monitoring, and security features. It is designed for developers who need a scalable, secure HTTP endpoint managed within a Kubernetes cluster.

How to use Model Context Protocol (MCP) Server?

Build the Docker image from the source directory, push it to an Azure Container Registry (ACR), then apply the Kubernetes manifests (k8s/) to deploy the server. After deployment, the server is accessible via the Kubernetes service. Scaling can be performed using kubectl scale deployment mcp-server --replicas=<number>.

Key features of Model Context Protocol (MCP) Server

  • HTTPS enabled for secure communication
  • CORS configured for cross-origin requests
  • Rate limiting implemented to prevent abuse
  • Helmet.js used for HTTP security headers
  • /health endpoint for Kubernetes health checks
  • Configurable via environment variables in a ConfigMap

Use cases of Model Context Protocol (MCP) Server

  • Hosting an MCP API in a production Kubernetes cluster
  • Horizontally scaling an HTTP service with multiple replicas
  • Monitoring application health and logs via Azure Monitor and kubectl logs
  • Securing an HTTP endpoint with HTTPS, CORS, and rate limiting

FAQ from Model Context Protocol (MCP) Server

What are the prerequisites to deploy this server?

Azure CLI, kubectl, Docker, and Node.js 18+.

How do I configure the server?

Configuration is set through environment variables defined in the Kubernetes ConfigMap (k8s/configmap.yaml).

How do I verify the server is running?

Check the pod and service status with kubectl get pods and kubectl get services. The server also exposes a /health endpoint for health checks.

What security measures are in place?

The server uses HTTPS, CORS configuration, rate limiting, and Helmet.js for security headers.

Can I scale the server?

Yes, the default deployment has 3 replicas. Use kubectl scale deployment mcp-server --replicas=<number> to adjust.

コメント

「その他」の他のコンテンツ