Provides a tool to connect to SSH servers and execute commands via an AI assistant.
Configuration
View docs{
"mcpServers": {
"mertcankaraoglu-ssh-mcp": {
"command": "npx",
"args": [
"-y",
"git+https://github.com/mertcankaraoglu/ssh-mcp.git#main"
]
}
}
}You can control remote servers using natural language through an AI assistant by running SSH commands via the SSH MCP Server. This enables you to connect to Linux VMs, cloud instances, and other SSH-accessible machines without opening a terminal, letting your AI fetch disk usage, inspect processes, or run any command you ask.
You interact with the SSH MCP Server through an MCP client (such as Claude Desktop or Cursor IDE). Start by connecting to a remote server using either a password or an SSH key. After a successful connection, ask your AI to execute commands in natural language and view results in real time.
Prerequisites you need before installation are Node.js version 18 or newer and access to an MCP-enabled client.
1. Install Node.js v18+ on your machine.
2. Add the SSH MCP server to your MCP configuration. The following JSON block should be placed inside your MCP config under mcpServers.
3. Restart the application so the AI can start using the new server.
{
"mcpServers": {
"ssh": {
"command": "npx",
"args": ["-y", "git+https://github.com/mertcankaraoglu/ssh-mcp.git#main"]
}
}
}If you need to install the server locally from source, you can clone the repository and run the installation steps. The SSH MCP Server is designed to be used as a local or remote MCP tool that your AI can call.
# Manual installation example
git clone https://github.com/mertcankaraoglu/ssh-mcp.git
cd ssh-mcp
npm install{
"mcpServers": {
"ssh": {
"command": "node",
"args": ["C:\\full\\path\\to\\ssh-mcp\\index.js"]
}
}
}Connects to an SSH server using host, username, and either a password or a key.
Runs a command on the connected SSH server and streams output in real time.
Closes the current SSH connection.