Allows managing Docker containers on remote servers, including starting, stopping, restarting, viewing logs, and status.
Allows querying InfluxDB v3 databases via SQL (read-only) on remote servers.
Allows querying Prometheus via PromQL and listing scrape targets on remote servers.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Remote Server MCP Check the status of the web server service"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A security-first MCP server that gives AI assistants controlled, safe access to manage remote servers via SSH.
Design principle: Whitelist operations, don't blacklist commands. No generic command execution — only 13 validated tools.
┌───────────────┐ ┌──────────────────────────────┐ ┌──────────────┐
│ AI Assistant │───▶│ MCP Server │───▶│ SSH to │
│ (Qwen Code) │◀───│ (Secure Tools Only) │◀───│ Remote │
└───────────────┘ │ │ │ Server │
│ Safe Tools: │ └──────────────┘
│ • list_services() │
│ • get_service_logs() │
│ • get_service_status() │
│ • restart/start/stop │
│ • get_service_file() │
│ • list_service_files() │
│ • search_service_logs() │
│ • get_server_health() │
│ • query_influxdb() │
│ • query_prometheus() │
│ • get_prometheus_targets() │
└──────────────────────────────┘
│
All commands validated
against security policy
before executionuv pip install -e . --python .venv
cp config.example.yaml config.yaml # edit with your SSH details
uv run pytest tests/ -vSee Getting Started for full setup instructions and Qwen Code integration.
Related MCP server: Simple SSH MCP Server
This project is a thin MCP server layer built on top of server-management-lib, which provides the core security validation, SSH management, and HTTP clients:
remote-server-mcp/ # This project — MCP server layer
├── src/remote_server_mcp/
│ ├── __init__.py # Entry point
│ └── server.py # MCP tool definitions (13 tools)
└── tests/
server-management-lib/ # Shared library (separate repo)
├── security.py # Security validator
├── ssh_manager.py # SSH connection handler
├── http_clients.py # InfluxDB + Prometheus clients
└── config.py # Configuration loader❌ No arbitrary command execution
❌ No file access outside /srv/{service}/
❌ No sensitive files (.env, .git/, *.key, secrets)
✅ Only specific, validated Docker operations
✅ All inputs sanitized against injection, traversal, and encoding bypasses
See Security Model for the full threat model and controls.
Tool | Purpose |
| List services in |
| Docker container logs |
| Status + resource usage |
| Restart container |
| Start container |
| Stop container |
| Read files in |
| List service directory |
| Search logs (plain text) |
| CPU / memory / disk metrics |
| Query InfluxDB v3 via SQL (read-only) |
| Query Prometheus via PromQL |
| List Prometheus scrape targets |
See Tools for detailed descriptions.
uv run ruff check . && uv run ruff format . && uv run ty check && uv run pytest tests/ -vSee Development for project structure, pre-commit hooks, and how to add new tools safely.
This tool is licensed under the terms of MIT license.
See LICENSE for more information.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Let AI operate servers without SSH. Choose actions, approve risky changes, and audit every step.
An MCP server for Arcjet - the runtime security platform that ships with your AI code.
Operate your Linux servers from your LLM. Every action runs through an auditable allowlist.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/elmuz/remote-server-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server