An MCP server for SSH connections and file operations.
An MCP server for SSH connections and file operations. The ssh mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 9 defined tools rather than through you.
The SSH connection parameters can be configured using environment variables in the MCP settings:
Everything the assistant can do here goes through one of these:
connect — Connect to an SSH serverdisconnect — Disconnect from the SSH serverexecute — Execute a command on the SSH serverupload — Upload a file to the SSH serverdownload — Download a file from the SSH serverlist_files — List files in a directory on the SSH serverTools — The Tools tool exposed by this serverTesting — A test script is provided in the tests directory to verify that the SSH MCP server is working correctly:Debugging — Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the [MCP@modelcontextprotocol/inspector on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
You will need 7 environment variables: SSH_HOST, SSH_PORT, SSH_USERNAME, SSH_PASSWORD, SSH_KEY_PATH, SSH_KEY_PASSPHRASE, UV_PUBLISH_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the file and storage access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Ssh's toolset — connect, disconnect, execute and 6 more — is a fair guide to whether it matches your workflow. It is maintained by t-suganuma; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| connect | Connect to an SSH server |
| disconnect | Disconnect from the SSH server |
| execute | Execute a command on the SSH server |
| upload | Upload a file to the SSH server |
| download | Download a file from the SSH server |
| list_files | List files in a directory on the SSH server |
| Tools | The Tools tool exposed by this server. |
| Testing | A test script is provided in the tests directory to verify that the SSH MCP server is working correctly: |
| Debugging | Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector). |
{
"mcpServers": {
"ssh-connect": {
"command": "uv",
"args": [
"--directory",
"/path/to/ssh-connect",
"run",
"ssh-connect"
],
"env": {
"SSH_HOST": "example.com",
"SSH_PORT": "22",
"SSH_USERNAME": "username",
"SSH_PASSWORD": "password",
"SSH_KEY_PATH": "/path/to/private_key",
"SSH_KEY_PASSPHRASE": "key_passphrase"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| SSH_HOST | Endpoint or connection string the server talks to. | Optional |
| SSH_PORT | Configuration value read at startup. | Optional |
| SSH_USERNAME | Configuration value read at startup. | Optional |
| SSH_PASSWORD | Configuration value read at startup. | Optional |
| SSH_KEY_PATH | Credential the server authenticates with. | Yes |
| SSH_KEY_PASSPHRASE | Credential the server authenticates with. | Yes |
| UV_PUBLISH_TOKEN | Credential the server authenticates with. | Yes |
Scoped local file access — read, write, search and reorganise files in directories you explicitly allow.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Connects AI models to an Obsidian knowledge base for direct access and manipulation of notes and folders.