Cover image
Try Now
2025-04-14

Patrón de sidecar de MCP en Kubernetes

3 years

Works with Finder

0

Github Watches

0

Github Forks

0

Github Stars

MCP Sidecar Pattern

MCP sidecar pattern on Kubernetes

Your can run MCP server only support stdio mode separetely from your app!

MCP Sidecar concept

sidecar image

Contents

Dockerfile-github-mcp-server

Sample Dockerfile to build GitHub MCP Server container(to add some tools to create FIFO pipe in GitHub MCP Server)

Dockerfile-client-app

Dockerfile for Sample Apps

mcp-sidecar-deploy.yaml

Kubernetes manifest to run a pod of AI app and MCP server sidecar

app.py

Sample python app to get your GitHub Repo list via MCP Server

mcp-proxy.py

Local proxy to bridge stdin/stdout pipe between app container and MCP Server sidecar container

How to run the sample app

  1. Build your app container with Dockerfile-client-app
  2. Build your GitHub MCP Server container with Dockerfile-github-mcp-server This is optional, only required for a MCP server container image without shell or mkfifo such as GitHub MCP Server
    • cd ~
    • git clone https://github.com/github/github-mcp-server.git
    • cd github-mcp-server
    • cp ../mcp-sidecar/Dockerfile-github-mcp-server .
    • docker build --tag your-built-github-mcp-server-image> -f Dockerfile-github-mcp-server .
    • docker push your-built-github-mcp-server-image>
  3. Run app on your Kubernetes
    • cd ../mcp-sidecar
    • kubectl create ns mcp
    • kubectl create secret generic github-token --from-literal=token=your GitHub PAT
    • kubectl apply -f MCP-sidecar-deploy.yaml
  4. Test your app
    • kubectl get pod -n mcp
    • kubectl exec github-mcp-sidecar-your-pod-name -it -- /bin/bash
    • python app.py Then, you can see list of your GitHub repos detail

Contributing

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

相关推荐

  • av
  • Ejecute sin esfuerzo LLM Backends, API, frontends y servicios con un solo comando.

  • 1Panel-dev
  • 🔥 1Panel proporciona una interfaz web intuitiva y un servidor MCP para administrar sitios web, archivos, contenedores, bases de datos y LLM en un servidor de Linux.

  • WangRongsheng
  • 🧑‍🚀 全世界最好的 llM 资料总结(数据处理、模型训练、模型部署、 O1 模型、 MCP 、小语言模型、视觉语言模型) | Resumen de los mejores recursos del mundo.

  • rulego
  • ⛓️Rulego es un marco de motor de regla de orquestación de componentes de alta generación de alto rendimiento, de alto rendimiento y de alto rendimiento para GO.

  • Onelevenvy
  • Flock es una plataforma de bajo código de flujo de trabajo para construir rápidamente chatbots, trapo y coordinar equipos de múltiples agentes, impulsados ​​por Langgraph, Langchain, Fastapi y Nextjs.

  • Byaidu
  • Traducción de papel científico en PDF con formatos preservados - 基于 Ai 完整保留排版的 PDF 文档全文双语翻译 , 支持 支持 支持 支持 支持 支持 支持 支持 支持 支持 支持 支持 等服务 等服务 等服务 提供 提供 提供 提供 提供 提供 提供 提供 提供 提供 提供 提供 cli/mcp/docker/zotero

  • n8n-io
  • Plataforma de automatización de flujo de trabajo de código justo con capacidades de IA nativas. Combine el edificio visual con código personalizado, auto-anfitrión o nube, más de 400 integraciones.

  • sigoden
  • Cree fácilmente herramientas y agentes de LLM utilizando funciones Plain Bash/JavaScript/Python.

  • hkr04
  • SDK liviano C ++ MCP (Protocolo de contexto del modelo)

  • RockChinQ
  • 😎简单易用、🧩丰富生态 - 大模型原生即时通信机器人平台 | 适配 Qq / 微信(企业微信、个人微信) / 飞书 / 钉钉 / Discord / Telegram / Slack 等平台 | 支持 Chatgpt 、 Deepseek 、 DiFy 、 Claude 、 Gemini 、 Xai 、 PPIO 、 Ollama 、 LM Studio 、阿里云百炼、火山方舟、 Siliconflow 、 Qwen 、 Moonshot 、 Chatglm 、 SillyTraven 、 MCP 等 LLM 的机器人 / Agente | Plataforma de bots de mensajería instantánea basada en LLM, admite Discord, Telegram, WeChat, Lark, Dingtalk, QQ, Slack

  • dmayboroda
  • Trapo conversacional local con contenedores configurables

    Reviews

    3.2 (5)
    Avatar
    user_Oi0JEimO
    2025-04-24

    I have been using mcp-sidecar for a while now, and it has truly transformed my multi-container management. Hats off to hatasaki for creating such a seamless application. The integration is smooth, and the performance is top-notch. Highly recommend this to anyone looking to optimize their container orchestration.

    Avatar
    user_osAqPUNt
    2025-04-24

    I've been using mcp-sidecar by hatasaki, and it has significantly streamlined my application management. It's intuitive and effectively enhances the user experience while maintaining robust functionality. Highly recommended for anyone looking to improve their app's performance.

    Avatar
    user_OzEwkV2x
    2025-04-24

    As a dedicated mcp user, I must say that mcp-sidecar has significantly enhanced my workflow. hatasaki has done an exceptional job with this tool, making it seamless and efficient. I highly recommend mcp-sidecar to anyone looking to optimize their application performance. The integration is smooth, and the user experience is top-notch. Great job!

    Avatar
    user_IWEEc12w
    2025-04-24

    As an avid user of the mcp application, I find the mcp-sidecar by hatasaki to be an indispensable addition. Its seamless integration and functionality significantly enhance the overall user experience. Whether you're new to MCP or a seasoned user, the mcp-sidecar is a must-have tool that exemplifies innovation and efficiency. Highly recommended!

    Avatar
    user_CsJ2XxIp
    2025-04-24

    I have been using the mcp-sidecar for a while, and it's an exceptional tool created by hatasaki. It integrates seamlessly with my setup, providing efficient and reliable performance. The design and user interface are very intuitive, making it easy to use even for someone new to such applications. Highly recommended for anyone looking to enhance their workflow!