SSH MCP servers: letting an AI agent run commands over SSH

11 November 2026 · Daniel Bilsborough · Reviewed 11 November 2026

An SSH MCP server is an MCP server whose tools run commands on a remote machine over SSH. Connect one to Claude, Cursor or another AI client, and the model can ask for df -h on your web server and read the answer without you typing anything.

It's one of two common ways to put an AI agent to work on a server. The other is to run the agent on the server itself and reach it over SSH, which is how Shell Drop is used. This page covers both, the security trade-offs of giving an agent SSH access, and what Shell Drop's own MCP server is (it is not an SSH MCP server).

What an MCP server is

MCP, the Model Context Protocol, is an open standard for connecting AI applications to outside tools and data. An MCP server offers a set of tools, each with a name, a description and the inputs it takes. An MCP client, such as Claude, Claude Code or Cursor, lists those tools to the model; when the model decides to use one, the client calls the server and hands the result back. A server can run on your own computer or as a remote service at a URL.

What people mean by an SSH MCP server

An MCP server whose tools reach a machine over SSH. A typical one offers tools along the lines of "run a command on this host", sometimes with file upload and download. The server holds or borrows SSH credentials, opens the connection, runs what the model asked for and returns the output.

The model never touches SSH directly. It sees tool names and results, and the MCP server is where the access really lives: which hosts it can reach, as which user, with which key, and whether it runs any command or only some.

Two ways to put an agent on a server

SSH MCP serverAgent on the server, reached over SSH
Where the agent runsOn your computer or in a cloud AI appOn the server, for example Claude Code or Codex inside Tmux
How it reaches the machineMCP tool calls, turned into SSH commandsIt's already there, with the permissions of the user it runs as
Where you watch itIn the AI app's conversationIn the terminal session, from any SSH client
Long jobsBounded by the AI app's session and each tool callKeeps running in Tmux after you disconnect
What has SSH credentialsThe MCP serverYou, to log in and check on it

An SSH MCP server suits quick, bounded jobs across several machines: checking disk space on five servers, reading a log, restarting a service. Running the agent on the server suits long work, a coding agent that builds, tests and edits for an hour, because the session lives where the work is and keeps going when you close the laptop or lock the phone.

The second model is the one Shell Drop is built around. Claude Code or Codex runs in a Tmux session on a Mac mini, a Linux box or a VPS, and you attach from an iPhone or iPad to read what it did and type the next instruction. Claude Code on iPhone and Codex on iPhone walk through that setup.

The security trade-offs of giving an agent SSH access

Either way, an agent with a shell can do what that account can do. A model that misreads an instruction, or follows one planted in a file or log it reads, acts with the same reach. The general precautions:

None of this is specific to MCP. The same applies to an agent running in Tmux on the server: it has whatever access the user who started it has.

What Shell Drop's MCP server is, and isn't

The Shell Drop MCP connector is not an SSH MCP server. It never connects to any machine and can't run a command anywhere.

It's a free, read-only help server at https://mcp.shelldrop.sh/mcp, with no account and no sign-in. It gives Claude and other AI tools step-by-step help for running coding agents on a Mac or Linux machine and reaching them from an iPhone or iPad. Its four tools:

Every tool returns text and never connects to or changes any machine. The server answers from fixed text and keeps nothing. Your AI client reads the answer, and you decide what to run. The MCP connector page has the endpoint and the setup lines for Claude, Claude Code and Cursor.

Questions

What is an SSH MCP server?

An MCP server whose tools run commands on a remote machine over SSH. An AI client such as Claude or Cursor calls a tool like “run this command on that host”, the MCP server makes the SSH connection, and the output goes back to the model.

Is the Shell Drop MCP connector an SSH MCP server?

No. It is a read-only help server: a setup guide, Tmux how-tos, a tmux.conf generator and connection troubleshooting. Every tool returns text and never connects to or changes any machine.

Is it safe to give an AI agent SSH access?

It can be, with limits: a separate user with only the permissions the job needs, a key used only by the agent, no broad sudo, and approval for anything that changes the system. Treat everything the agent reads on the server as possibly carrying instructions.

Do I need an SSH MCP server to use Claude Code on a server?

No. Claude Code and Codex can run on the server itself, inside Tmux, with the access of the user you start them as. You then reach that session over SSH from a laptop, an iPhone or an iPad.

Get Shell Drop on the App Store QR code for Shell Drop on the App Store Reading on a computer? Scan the code with your iPhone camera.