MCP SSH Gateway MCP server

<!-- mcp-name: io.github.d00mus/mcp-ssh-gateway -->

MCP SSH Gateway

Use your MCP client to work with several SSH hosts through one local connection. Run diagnostics on a VPS, inspect a NAS or query a Keenetic router by name. Sessions preserve terminal state between calls; long output can be read a page at a time.

For people who already use SSH and want an assistant to help with routine diagnostics and administration. It is not an SSH daemon, a hosted proxy or a replacement for access controls on your servers.

Try it with one host

You need Python 3.11+, an SSH account on a host you control and an MCP client that can launch a local stdio server.

1. Install it:

python -m pip install mcp-ssh-gateway

Or run it without installing anything: uvx --from mcp-ssh-gateway mcp-ssh-gateway --servers-config servers.json

To work on the project itself, clone it instead: git clone https://github.com/d00mus/MCP-SSH.git && cd MCP-SSH && python -m pip install -r requirements.txt

1. Create a servers.json somewhere you will remember (replace the address, user and key path with your own):

{
     "servers": {
       "lab": {
         "host": "192.168.1.10",
         "user": "your-ssh-user",
         "key_path": "~/.ssh/id_ed25519"
       }
     }
   }

Host-key verification is enabled by default and uses the machine’s system host-key store. Ensure the host key is already trusted there, and verify its fingerprint independently before adding it. For password authentication, use "password": "${LABSSHPASSWORD}" and provide LABSSHPASSWORD to the MCP server process. Do not commit real credentials or your servers.json. See the security policy.

1. Add this to a client that uses the mcpServers config format. Replace the absolute path: clients do not necessarily start in your working directory.

{
     "mcpServers": {
       "ssh-gateway": {
         "command": "mcp-ssh-gateway",
         "args": ["--servers-config", "/absolute/path/to/servers.json"]
       }
     }
   }

On Windows, point command at mcp-ssh-gateway.exe in your Python Scripts directory if the client does not resolve it from PATH, and use escaped backslashes in JSON paths (for example C:\\Users\\you\\servers.json).

Running the command directly is not an interactive SSH terminal: it communicates with the client over stdio. Restart the MCP client after updating its config.

1. In the client, ask: “List my SSH hosts, then run uname -a on lab.” If the host is missing, check the config path and the client's MCP server logs. If SSH fails, check credentials and host-key verification.

Add more hosts under servers in the same file. servers.json.example shows a multi-host configuration; check its host-key and credential choices before copying it.

What using it looks like

A Linux host and a router can share one MCP connection. Your client makes calls like these (they are not terminal commands):

server_list()                                          # find configured hosts
run(server="lab", command="df -h")                  # inspect disk space
run(server="keenetic", command="show interface", shell=false)  # router CLI

Shortened. The full README is on GitHub.