MCPgee
MCPgee
MCPgeeMCPgee

Deploystack

v1.0.0•Cloud Services•stable

Open source MCP hosting - deploy MCP servers to HTTP endpoints for n8n, Dify, Voiceflow, and any MCP client.

deploystackmcpmcp-servermodel-context-protocolnodejs
Share:
57
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Deploystack?

Deploystack is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to open source mcp hosting - deploy mcp servers to http endpoints for n8n, dify, voiceflow, and any mcp client.

Open source MCP hosting - deploy MCP servers to HTTP endpoints for n8n, Dify, Voiceflow, and any MCP client.

This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Open source MCP hosting - deploy MCP servers to HTTP endpoin

Use Cases

Deploy MCP servers to HTTP endpoints.
Integrate MCP with n8n, Dify, and Voiceflow.
Host MCP servers as cloud services.
deploystackio

Maintainer

LicenseAGPL-3.0
Languagetypescript
Versionv1.0.0
UpdatedMay 3, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx deploystack

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Deploystack

DeployStack is an open-source MCP hosting platform that deploys MCP servers to persistent HTTP endpoints, solving the limitation that stdio-based MCP servers cannot be used by workflow platforms like n8n, Dify, Voiceflow, or Langflow that require HTTP access. It implements a hierarchical router pattern exposing only two meta-tools (discover_mcp_tools and execute_mcp_tool), which reduces context window usage by up to 98% compared to loading all tool schemas at once. Teams use it to centrally host, version, and secure MCP servers with a credential vault, RBAC, and audit logging.

Prerequisites

  • Docker and Docker Compose installed (for self-hosted setup)
  • Git to clone the repository
  • A GitHub account (for OAuth authentication and repository-based deployments)
  • An MCP-compatible client or workflow platform that supports HTTP/SSE MCP endpoints (n8n, Dify, Claude Code, Cursor, etc.)
1

Clone the DeployStack repository

Clone the repository to your server or local machine. The project includes a docker-compose.yml for the full stack.

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

Start the platform with Docker Compose

Bring up all services (backend, frontend, database) with a single command. The platform will be available at http://localhost:3000 by default.

docker-compose up
3

Connect your GitHub account

Open http://localhost:3000 in a browser and complete GitHub OAuth. This allows DeployStack to deploy MCP servers directly from your repositories and manage credentials securely.

4

Deploy an MCP server from the catalog or a repository

Browse the built-in server catalog for pre-configured servers (one-click install), or connect a GitHub repository containing an MCP server — it will auto-deploy on push.

5

Add credentials to the vault

Store API keys and secrets in the Credential Vault. DeployStack injects them at runtime so they never appear in config files or chat logs.

6

Connect an MCP client to the HTTP endpoint

Copy the HTTP endpoint URL for your deployed server and add it to your MCP client configuration. The cloud-hosted endpoint is at satellite.deploystack.io.

{
  "mcpServers": {
    "deploystack": {
      "type": "http",
      "url": "https://satellite.deploystack.io/mcp"
    }
  }
}

Deploystack Examples

Client configuration (cloud-hosted endpoint)

MCP client configuration to connect to the DeployStack cloud-hosted router endpoint.

{
  "mcpServers": {
    "deploystack": {
      "type": "http",
      "url": "https://satellite.deploystack.io/mcp"
    }
  }
}

Prompts to try

Example prompts once an MCP client is connected to a DeployStack endpoint.

- "Discover what MCP tools are available on my DeployStack instance."
- "Deploy the GitHub MCP server from the catalog and give me the endpoint URL."
- "List all MCP servers currently hosted on DeployStack and their status."
- "Execute the filesystem read tool on my hosted server to read /etc/hostname."
- "Update the API key stored in the credential vault for my weather MCP server."

Troubleshooting Deploystack

docker-compose up fails with port conflict errors

Edit docker-compose.yml to change the host port mappings if ports 3000 or 9000 are already in use on your machine. Update the frontend API base URL env variable to match the new backend port.

MCP client receives 'tool not found' when calling a tool

DeployStack uses a two-step pattern: first call discover_mcp_tools to find the tool name, then call execute_mcp_tool with that name. Direct tool names from the underlying server are not exposed at the router level.

GitHub OAuth redirect fails during login

Ensure the GitHub OAuth app callback URL is set to http://localhost:3000/auth/callback (or your deployment domain). Update this in your GitHub Developer Settings under the OAuth App configuration.

Frequently Asked Questions about Deploystack

What is Deploystack?

Deploystack is a Model Context Protocol (MCP) server that open source mcp hosting - deploy mcp servers to http endpoints for n8n, dify, voiceflow, and any mcp client. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Deploystack?

Follow the installation instructions on the Deploystack GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Deploystack?

Deploystack works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Deploystack free to use?

Yes, Deploystack is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Deploystack Alternatives — Similar Cloud Services Servers

Looking for alternatives to Deploystack? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.

Open WebUI

★ 138.2k

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Anything LLM

★ 60.4k

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

LocalAI

★ 46.4k

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Nacos

★ 33.0k

an easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.

Xiaozhi ESP32

★ 26.7k

本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.

Gateway

★ 11.8k

A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Browse More Cloud Services MCP Servers

Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Cloud ServicesBrowse All Servers

Quick Config Preview

{ "mcpServers": { "deploystack": { "command": "npx", "args": ["-y", "deploystack"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Deploystack?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides