Remote SSH Terminal MCP - AI-Powered Linux Server Management

@TiM00R

About Remote SSH Terminal MCP - AI-Powered Linux Server Management

AI-Powered Remote Linux Server Management via MCP - Let Claude execute commands on your servers

#ssh #mcp #claude #linux #remote-server #terminal #ai-automation #devops #server-management #sftp #batch-scripts #claude-desktop #model-context-protocol

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "remote-terminal": {
      "command": "C:\\RemoteTerminal\\venv\\Scripts\\remote-terminal-mcp.exe",
      "env": {
        "REMOTE_TERMINAL_ROOT": "C:\\RemoteTerminal"
      }
    }
  }
}

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 Remote SSH Terminal MCP - AI-Powered Linux Server Management?

Remote SSH Terminal MCP is an MCP server that lets Claude execute commands on remote Linux servers through a natural chat interface. It provides an interactive web terminal for full real‑time visibility while Claude receives token‑efficient filtered summaries, enabling AI‑powered server management.

How to use Remote SSH Terminal MCP - AI-Powered Linux Server Management?

Install the package via pip install remote-terminal-mcp in a Python virtual environment, then configure Claude Desktop by adding the server command to claude_desktop_config.json. On first run, configuration files (config.yaml, hosts.yaml) are auto‑created. Edit the hosts file to add your servers, restart Claude Desktop, and start giving commands like "Install nginx" or "Check disk space".

Key features of Remote SSH Terminal MCP - AI-Powered Linux Server Management

Remote command execution on Linux servers
Multi‑server management with easy switching
File transfer (SFTP) with compression support
Batch script execution (10‑50x faster)
Saved batch script library and recipe system
Full audit trail with SQLite database
Interactive web terminal with real‑time output
Multi‑terminal synchronization via WebSocket broadcast

Use cases of Remote SSH Terminal MCP - AI-Powered Linux Server Management

System administration: check disk space, memory, processes
Software management: install, update, verify packages
Troubleshooting: analyze logs, diagnose network issues
File operations: upload/download files, find large files
Automation: create and reuse recipes for routine tasks

FAQ from Remote SSH Terminal MCP - AI-Powered Linux Server Management

What is the difference between the web terminal and what Claude sees?

The web terminal shows the full raw output from the remote server, while Claude receives a smart filtered summary that saves up to 95% of tokens. Both share the same SSH session, so you maintain full visibility and control.

How do I install and configure the server?

Run pip install remote-terminal-mcp in a Python virtual environment, then add the command to your Claude Desktop config. On first use, default configuration files are copied to the installation directory. Edit hosts.yaml to add your servers.

What are the runtime requirements?

The server runs on Windows (tested), requires Python 3.8+, and the remote-terminal-mcp package. A virtual environment is recommended. The web interface is accessed via a browser at http://localhost:8080 (terminal) and http://localhost:8081 (control panel).

Where is data stored?

All command history, conversations, recipes, and batch scripts are stored in a local SQLite database at <installation>/data/remote_terminal.db. No data is sent to external servers.

What transport and authentication are used?

The MCP server communicates with Claude Desktop via stdio. Remote server connections use SSH (password authentication configured in hosts.yaml). The web terminal uses WebSocket for real‑time updates and is accessible only on localhost.

Frequently asked questions

What is the difference between the web terminal and what Claude sees?

How do I install and configure the server?

Run `pip install remote-terminal-mcp` in a Python virtual environment, then add the command to your Claude Desktop config. On first use, default configuration files are copied to the installation directory. Edit `hosts.yaml` to add your servers.

What are the runtime requirements?

The server runs on Windows (tested), requires Python 3.8+, and the `remote-terminal-mcp` package. A virtual environment is recommended. The web interface is accessed via a browser at `http://localhost:8080` (terminal) and `http://localhost:8081` (control panel).

Where is data stored?

All command history, conversations, recipes, and batch scripts are stored in a local SQLite database at `<installation>/data/remote_terminal.db`. No data is sent to external servers.

What transport and authentication are used?

The MCP server communicates with Claude Desktop via stdio. Remote server connections use SSH (password authentication configured in `hosts.yaml`). The web terminal uses WebSocket for real‑time updates and is accessible only on localhost.

Comments

Basic information

More Developer Tools MCP servers

FastAPI-MCP

tadata-org

Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!

11.9K

Unity MCP (Server + Plugin)

IvanMurzak

AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for fr

3.5K

mcp-excalidraw

yctimlin

MCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.

2.1K

Serena

oraios

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

26.2K

OpenSumi

opensumi

A framework helps you quickly build AI Native IDE products. MCP Client, supports Model Context Protocol (MCP) tools via MCP server.

3.6K