Sponsored by Deepsite.site

DeployStack

Created By
deploystackio7 months ago
Deploy MCP servers without the hassle. Purpose-built CI/CD platform that eliminates the technical complexity of MCP server deployment, credential management, and production scaling.
Content

DeployStack

DeployStack


DeployStack is an open-source CI/CD platform specifically built for MCP (Model Context Protocol) servers. Think of us as the infrastructure layer that makes MCP server deployment as simple as using n8n for automations - you select your MCP server, configure credentials, choose your target platform, and we handle all the complex deployment work behind the scenes.

What Makes DeployStack Different

  • MCP-Native CI/CD: Purpose-built for MCP server lifecycle management, not adapted from general deployment tools
  • Multi-Cloud Excellence: Deploy MCP servers to AWS, Render.com, Fly.io, DigitalOcean, and more with one click
  • Enterprise-Ready: Team collaboration, private catalogs, and security features for organizations
  • Community-Driven: Open-source foundation with curated MCP server catalog
  • Developer Experience Focus: Eliminates the technical complexity that currently limits MCP adoption

The MCP Server Deployment Problem

MCP servers are experiencing explosive adoption, with Claude Desktop leading the way as the primary integration point for AI agents. However, deploying MCP servers presents significant challenges that DeployStack addresses:

Current Pain Points We Solve

1. Technical Complexity Barriers Getting up and running with MCP servers is a headache for developers, with basic examples requiring hundreds of lines of code and complex dependency management

2. Security and Credential Management Users are asked to configure sensitive data in plaintext JSON files, and MCP currently lacks standardized authentication mechanisms for client-server interactions

3. Production Deployment Gaps Most MCP servers are designed for local development, with transport protocols like stdio that won't work in production environments

4. Multi-Tenant Architecture Challenges Current MCP servers are often single-user, and multi-tenancy (one MCP server serving multiple independent agents or users) is not much explored yet

5. Fragmented Discovery As more MCP servers are developed, mechanisms for discovering trusted and maintained servers are needed, with broader solutions for standardization still required

Core Features

  • One-Click MCP Deployment: Deploy any MCP server to production instantly across multiple cloud providers
  • Secure Credential Management: Encrypted storage and injection of API keys, OAuth tokens, and secrets
  • Team Collaboration: Role-based access control, shared configurations, and organizational management
  • Internal MCP Catalogs: Private, company-specific MCP server catalogs for enterprise deployments
  • Multi-Tenant MCP Servers: Deploy scalable MCP servers that serve multiple users and agents
  • Authentication Proxy: Built-in OAuth handling and security gateway for MCP server access
  • Community Catalog Integration: Seamless connection to our curated MCP server ecosystem

MCP Server Ecosystem

DeployStack integrates with the broader MCP ecosystem to provide comprehensive infrastructure:

Getting Started

🚀 Quick Start with DeployStack Cloud

The fastest way to deploy MCP servers and solve the current deployment challenges:

  1. Sign up for free: cloud.deploystack.io
  2. Browse MCP servers: Choose from our curated catalog of production-ready servers
  3. Configure securely: Add your credentials through our encrypted management system
  4. One-click deploy: Select your cloud provider and deploy with enterprise-grade security (security = still in progress)
  5. Connect to MCP Server: Use generated connection details in Claude Desktop, VS Code, or other MCP-compatible tools

🛠️ Self-Hosted Installation

You can also run DeployStack on your own infrastructure for maximum control:

Prerequisites

  • Node.js 18 or higher
  • npm 8 or higher
  • Docker

Installation

  1. Clone the repository:

    git clone https://github.com/deploystackio/deploystack.git
    cd deploystack
    
  2. Install dependencies:

    npm install
    
  3. Start development servers:

Create a services/backend/.env file in the root directory with the following content:

DEPLOYSTACK_FRONTEND_URL=http://localhost:5173
DEPLOYSTACK_ENCRYPTION_SECRET=your-very-secure-32-character-secret-key-here
# Start frontend development server
npm run dev:frontend

# In another terminal, start backend server
npm run dev:backend

Deploying with Docker

Alternatively, you can deploy the pre-built Docker images for the frontend and backend services.

  1. Pull the latest images from Docker Hub:

    docker pull deploystack/frontend:latest
    docker pull deploystack/backend:latest
    
  2. Run the Backend Service:

    The backend requires a persistent volume for its data (like database configuration and SQLite files). The following command maps a local directory (./services/backend/persistent_data) to the container's data directory. It's recommended to run this command from the root of the cloned DeployStack project directory.

    docker run -d \
      -p 3000:3000 \
      -e DEPLOYSTACK_FRONTEND_URL="http://localhost:8080" \
      -e DEPLOYSTACK_ENCRYPTION_SECRET="your-very-secure-32-character-secret-key-here" \
      -v $(pwd)/services/backend/persistent_data:/app/persistent_data \
      deploystack/backend:latest
    
  3. Run the Frontend Service:

    The frontend requires environment variables to connect to the backend and for other configurations.

    docker run -d -p 8080:80 \
      -e VITE_DEPLOYSTACK_BACKEND_URL="http://localhost:3000" \
      -e VITE_APP_TITLE="DeployStack Instance" \
      deploystack/frontend:latest
    

    Note:

    • Ensure the VITE_DEPLOYSTACK_BACKEND_URL points to where your backend service is accessible. If running both containers on the same Docker host, http://localhost:3000 (or the host's IP/hostname if localhost doesn't resolve correctly from within the frontend container's network to the backend's exposed port) should work.
    • The $(pwd) in the backend command assumes you are in the root of the deploystack project directory. Adjust the path to services/backend/persistent_data if running from elsewhere, or use an absolute path or a Docker named volume.

Production Deployment

For production deployments on a VPS or remote server, update the environment variables to use your server's IP address:

Backend:

docker run -d \
  -p 3000:3000 \
  -e DEPLOYSTACK_FRONTEND_URL="http://YOUR_SERVER_IP:8080" \
  -e DEPLOYSTACK_ENCRYPTION_SECRET="your-very-secure-32-character-secret-key-here" \
  -v $(pwd)/services/backend/persistent_data:/app/persistent_data \
  deploystack/backend:latest

Frontend:

docker run -d -p 8080:80 \
  -e VITE_DEPLOYSTACK_BACKEND_URL="http://YOUR_SERVER_IP:3000" \
  -e VITE_APP_TITLE="DeployStack Instance" \
  deploystack/frontend:latest

Project Structure

This repository uses a monorepo structure optimized for MCP server deployment:

deploystack/
├── services/
│   ├── frontend/        # Vue.js frontend application
│   ├── backend/         # Fastify backend API
│   └── shared/          # Shared MCP utilities and types
├── scripts/             # MCP deployment automation scripts
├── templates/           # Cloud provider templates for MCP servers
└── ...

Contributing to the MCP Ecosystem

We welcome contributions to both the platform and the MCP server catalog:

Contributing MCP Servers

Add your MCP server to our community catalog:

  1. Fork awesome-mcp-server
  2. Add your server following the contribution guidelines
  3. Submit a pull request

Your MCP server will automatically appear in the DeployStack catalog once merged, with full deployment automation.

Contributing to the Platform

  1. Fork this repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes following our commit guidelines
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

For detailed contribution guidelines, see CONTRIBUTING.md.

Community and Support

  • Discord: Join our community at discord.gg
  • GitHub Discussions: Ask questions and share ideas about MCP server deployment
  • Documentation: Visit deploystack.io/docs for comprehensive guides
  • Twitter: Follow @deploystack for MCP ecosystem updates

Roadmap

View our detailed roadmap at deploystack.io/roadmap.

License

This project is licensed under the DeployStack License (DSL), a permissive license that allows for almost all uses except offering the software as a cloud service that competes with DeployStack's offerings. See the LICENSE file for details.


Ready to solve MCP server deployment challenges? Get started for free →

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
WindsurfThe new purpose-built IDE to harness magic
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Amap Maps高德地图官方 MCP Server
Playwright McpPlaywright MCP server
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
CursorThe AI Code Editor
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
Tavily Mcp
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
DeepChatYour AI Partner on Desktop
Serper MCP ServerA Serper MCP Server
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
ChatWiseThe second fastest AI chatbot™
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.