How do I install Dmcps?

Dmcps is a local plugin. Install it using the provided package and add the generated configuration snippet to your AI app's MCP config file. Then restart your AI app.

Is Dmcps safe to use?

Dmcps was flagged by MCP Marketplace's security scan, scoring 3.2/10 (high risk). It has 8 high or critical findings to review. Review the security report on this page carefully before installing it.

What AI apps work with Dmcps?

Dmcps uses the Model Context Protocol (MCP) and works with any MCP-compatible AI app, including Claude, ChatGPT / Codex, Gemini, Copilot, Cursor, and more.

Back to Browse

Dmcps MCP Server

by RMAAPK

Developer ToolsUse Caution3.2MCP RegistryLocal

Free

Server data from the Official MCP Registry

DMCPS: Highly secure, isolated MCP server environment giving AI agents sandboxed shell access.

About

DMCPS: Highly secure, isolated MCP server environment giving AI agents sandboxed shell access.

Security Report

3.2

Use Caution3.2High Risk

This MCP server has critical security vulnerabilities that undermine its stated security guarantees. The shell command execution lacks proper escaping, allowing command injection attacks. The OAuth2 implementation is a bypass mechanism rather than actual authentication. Authorization checks are applied inconsistently across multiple code paths, and sensitive operations use weak authentication (single static password). While the codebase shows good intent around sandboxing, these implementation flaws create real attack surfaces that users should understand. Supply chain analysis found 1 known vulnerability in dependencies (0 critical, 1 high severity).

5 files analyzed · 17 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

HTTP Network Access

Connects to external APIs or services over the internet.

Shell Command Execution

Runs commands on your machine. Be cautious — only use if you trust this plugin.

File System Read

Reads files on your machine. Normal for tools that analyze or process local data.

File System Write

Writes or modifies files on your machine. Check that this is expected for the tool.

process_spawn

Check that this permission is expected for this type of plugin.

env_vars

Check that this permission is expected for this type of plugin.

system_info

Check that this permission is expected for this type of plugin.

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "io-github-thealidev-dmcps": {
      "args": [
        "-y",
        "dmcps"
      ],
      "command": "npx"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

Docker SSH MCP - Sandbox

A highly secure, isolated Model Context Protocol (MCP) server environment designed to give AI agents access to a sandboxed filesystem and shell execution, without compromising the host machine.

🚀 Pure IPv4 Elastic IP Architecture (Zero Tunnels)

Why we abandoned Ngrok, Cloudflare Relay, and localhost.run: When connecting sophisticated agents like Google Gemini, we discovered that traditional tunnel services break the delicate MCP Server-Sent Events (SSE) stream:

Ngrok / localhost.run: Interstitial warning screens ("Visit Site" buttons) completely break Gemini's automated API handshake and metadata discovery.
Cloudflare Tunnels: Strict HTTP/2 WebSocket limitations, aggressive timeouts, and anti-bot verification pages drop long-running agent shell execution streams.

The Solution: DMCPS now runs on a Pure Elastic IPv4 Address backed by an automatic Caddy Reverse Proxy. This provides a direct, un-proxied (no middleman), low-latency connection with an auto-renewing Let's Encrypt SSL certificate via sslip.io. Gemini connects instantly, sees valid CORS headers, and never drops the stream.

1. Configure Environment

Create a .env file on your server (do not commit this):

ADMIN_USERNAME=admin
ADMIN_PASSWORD=supersecret
DOMAIN_NAME=16.176.42.41.sslip.io

(Replace the IP with your AWS Elastic IP)

2. Deploy on AWS (Docker Compose)

Run the provided stack which instantly spins up the MCP Server and the Caddy SSL reverse proxy:

docker compose up -d --build

3. Connect to Gemini (Cursor on your Phone)

Open the Gemini App (or gemini.google.com).
Go to Settings > Connected Apps.
Scroll to the bottom and click Add a custom app.
Enter your endpoint URL (e.g. https://16.176.42.41.sslip.io/sse).
Authenticate and connect!

Enjoy absolute, unrestricted shell and file access right from your mobile device!

Reviews

No reviews yet

Be the first to review this server!

4.8

Local

mcp-creator-python

Free

by mcp-marketplace · Developer Tools

Create, build, and publish Python MCP servers to PyPI — conversationally.

Dmcps MCP Server

About

Security Report

Findings (17)Action required

Permissions Required

How to Install

Documentation

Docker SSH MCP - Sandbox

🚀 Pure IPv4 Elastic IP Architecture (Zero Tunnels)

1. Configure Environment

2. Deploy on AWS (Docker Compose)

3. Connect to Gemini (Cursor on your Phone)

Reviews

No reviews yet

More Developer Tools MCP Servers

Git

Fetch

Worldmonitor

Paperclip

Toleno

mcp-creator-python