DeployStack
@deploystackio
About DeployStack
Open source MCP hosting - deploy MCP servers to HTTP endpoints for n8n, Dify, Voiceflow, and any MCP client.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"deploystack": {
"type": "http",
"url": "https://satellite.deploystack.io/mcp"
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is DeployStack?
DeployStack is an open-source platform that hosts MCP (Model Context Protocol) servers as HTTP/SSE endpoints, integrating with GitHub to deploy any stdio MCP server in seconds. It is designed for users of workflow automation platforms like n8n, Dify, Voiceflow, Langflow, and AI coding tools like Claude Code and Cursor, eliminating the need for local setup or DevOps.
How to use DeployStack?
Sign up at cloud.deploystack.io, then deploy MCP servers from GitHub repositories or install from the curated catalog. Configure your MCP client with a single HTTP URL (e.g., https://satellite.deploystack.io/mcp) to access all team MCP tools. For self-hosting, run docker-compose up after cloning the repository.
Key features of DeployStack
- Deploys stdio MCP servers to HTTP endpoints in 30 seconds.
- Hierarchical router reduces token usage by 98%.
- Encrypted credential vault with automatic injection.
- Team management with role-based access control.
- Audit logging for complete tool interaction visibility.
- Works with any MCP client supporting HTTP/SSE.
Use cases of DeployStack
- Connect MCP servers to n8n, Dify, or Voiceflow without stdio limitations.
- Manage and rotate API keys centrally across a team.
- Onboard new developers instantly with one shared MCP endpoint.
- Self-host MCP servers on company infrastructure with full data control.
FAQ from DeployStack
How does DeployStack make MCP servers available to HTTP clients?
It uses a satellite infrastructure that converts stdio-based MCP servers into HTTP/SSE endpoints, which can be consumed by any MCP client that supports HTTP transport.
What kind of token reduction does the hierarchical router achieve?
The router exposes only two meta-tools (discover and execute), achieving up to 98% token reduction compared to loading all tools from multiple servers into context.
Where are credentials stored?
Credentials are stored in an encrypted vault at rest and automatically injected at runtime. They are never placed in config files or shared via Slack.
Can I self-host DeployStack?
Yes, DeployStack is open-source under AGPL-3.0. You can run it on your own infrastructure using Docker Compose.
What MCP clients are supported?
It works with any MCP client that supports HTTP/SSE, including n8n, Dify, Voiceflow, Langflow, Claude Code, Cursor, VS Code, Windsurf, and custom integrations.
Frequently asked questions
How does DeployStack make MCP servers available to HTTP clients?
It uses a satellite infrastructure that converts stdio-based MCP servers into HTTP/SSE endpoints, which can be consumed by any MCP client that supports HTTP transport.
What kind of token reduction does the hierarchical router achieve?
The router exposes only two meta-tools (discover and execute), achieving up to 98% token reduction compared to loading all tools from multiple servers into context.
Where are credentials stored?
Credentials are stored in an encrypted vault at rest and automatically injected at runtime. They are never placed in config files or shared via Slack.
Can I self-host DeployStack?
Yes, DeployStack is open-source under AGPL-3.0. You can run it on your own infrastructure using Docker Compose.
What MCP clients are supported?
It works with any MCP client that supports HTTP/SSE, including n8n, Dify, Voiceflow, Langflow, Claude Code, Cursor, VS Code, Windsurf, and custom integrations.
Basic information
More Other MCP servers
Website
FunnyWolfAdversary simulation and Red teaming platform with AI

DeepMark
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
MCP Registry
modelcontextprotocolA community driven registry service for Model Context Protocol (MCP) servers.
Blender
ahujasidOpen-source MCP to use Blender with any LLM
Comments