An add-on that connects Claude Code to remote computers through SSH, a secure way to run commands on another machine. It is described as supporting Linux, Windows, Docker, Kubernetes, and air-gapped hosts that are isolated from networks.

Use it for remote server administration and for running commands on remote operating-system, container, or Kubernetes environments.

It removes the need to manage those remote systems only by logging into them separately. The available description does not provide more detail about its individual tools or limits.

bridge-mcp — Plugin by muchiny

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add muchiny/bridge-mcp

agentmods

npx agentmods add plugins/muchiny/bridge-mcp/plugin

Clone the repo

git clone --depth 1 https://github.com/muchiny/bridge-mcp

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

bridge-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/.claude-plugin/plugin.json · 25 lines

What it actually says

{
  "name": "bridge-mcp",
  "version": "3.0.0",
  "description": "476-tool SSH bridge for secure remote server management. Execute commands on air-gapped Linux, Windows, Docker, Kubernetes hosts via SSH from Claude Code.",
  "author": {
    "name": "muchiny",
    "url": "https://github.com/muchiny"
  },
  "homepage": "https://github.com/muchiny/bridge-mcp",
  "repository": "https://github.com/muchiny/bridge-mcp",
  "license": "MIT",
  "keywords": ["ssh", "remote", "devops", "docker", "kubernetes", "linux", "windows"],
  "skills": "./skills/",
  "mcpServers": "./.mcp.json",
  "hooks": "./hooks/hooks.json",
  "userConfig": {
    "config_path": {
      "type": "file",
      "title": "Config path",
      "description": "Path to your bridge-mcp config.yaml (default: ~/.config/bridge-mcp/config.yaml)",
      "sensitive": false
    }
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 25 lines scan A 7b39e5a2d316

Subscribe to this mod's changes

bridge-mcp is a plugin published in the GitHub repository muchiny/bridge-mcp (8 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI DevOps and cloud Security ai-tools air-gapped automation claude claude-code compliance

bridge-mcp

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

epa-mcp-server

fedramp-ssp

safe-android-reverser

clipboard-mcp-server

memvid

lovstudio-cc-plugins