io.github.NikolaNddTesla/sshmcp
SSH server management with zero-token SFTP file transfer and SOCKS proxy support
Ask AI about io.github.NikolaNddTesla/sshmcp
Powered by Claude Β· Grounded in docs
I know everything about io.github.NikolaNddTesla/sshmcp. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
@nl4ever/sshmcp
Let AI manage your remote servers. A Model Context Protocol (MCP) server that gives AI assistants full SSH access β execute commands, transfer files, manage multiple servers simultaneously, all through natural conversation.
You: "Deploy the latest build to production server"
AI: connects β uploads build β restarts service β verifies status
Features
- 21 Tools β Connect, execute, upload, download, write files, and more
- Connection Pool β Operate multiple servers simultaneously, each command tagged with
server_id - Zero-Token File Transfer β SFTP path-based transfer, file content never enters AI context
- Directory Upload β Auto tar.gz compress β upload β remote decompress (fast for many small files)
- Async Transfer + Progress β Background transfer for large files with real-time progress tracking
- Quick Connect β Temporary connections without saving config, returns
host:portas temp ID - SOCKS4/5 Proxy β Per-connection proxy support
- Jump Host β SSH ProxyJump for bastion/gateway access
- Multi-Auth β Password, private key, ssh-agent, keyboard-interactive (OTP/2FA)
Quick Start
Install globally
npm install -g @nl4ever/sshmcp
Add to Claude Code
claude mcp add sshmcp sshmcp
Add to Claude Desktop
Edit claude_desktop_config.json:
{
"mcpServers": {
"sshmcp": {
"command": "npx",
"args": ["-y", "@nl4ever/sshmcp"]
}
}
}
Add to Cursor
Go to Settings β MCP Servers β Add:
{
"sshmcp": {
"command": "npx",
"args": ["-y", "@nl4ever/sshmcp"]
}
}
Tools Overview
Connection Management
| Tool | Description |
|---|---|
list_servers | List all configured servers and active connections |
get_server | View server config details |
add_server | Add/update server config (password, key, agent, OTP) |
update_server | Modify server config (only pass fields you want to change) |
delete_server | Remove a server |
rename_server | Rename a server ID |
connect | Manually connect (usually not needed, tools auto-connect) |
quick_connect | Temporary connection, returns host:port as ID |
disconnect | Disconnect specific server or all connections |
test_connection | Test connectivity without affecting existing connections |
Command Execution
| Tool | Description |
|---|---|
execute | Run shell commands on remote server (with configurable timeout) |
File Operations
| Tool | Description |
|---|---|
read_file | Read remote file content (with optional line range) |
write_file | Write text content to remote file |
upload_file | Upload local file to remote (supports async mode) |
upload_directory | Upload directory with auto compress β transfer β decompress |
download_file | Download remote file to local (supports async mode) |
download_directory | Download directory with remote compress β transfer β local decompress |
transfer_status | Check progress of async transfers (size/speed/ETA) |
Proxy Management
| Tool | Description |
|---|---|
list_proxies | List all SOCKS proxy presets |
add_proxy | Add SOCKS4/5 proxy preset |
delete_proxy | Remove a proxy preset |
Connection Pool: Multi-Server Operations
All operation tools take a server_id parameter. The connection pool auto-manages connections β no manual connect/disconnect needed:
AI: execute(server_id="prod", command="nginx -s reload") β auto-connects to prod
AI: execute(server_id="dev", command="tail -f /var/log/app.log") β auto-connects to dev, prod stays
AI: execute(server_id="prod", command="curl localhost") β reuses prod connection
For temporary servers, use quick_connect which returns host:port as the ID:
AI: quick_connect(host="1.2.3.4", username="root", password="***")
β "Connected: root@1.2.3.4:22, use server_id="1.2.3.4:22""
AI: execute(server_id="1.2.3.4:22", command="df -h")
AI: disconnect(server_id="1.2.3.4:22")
Async Transfer (Large Files)
For large files, enable background transfer mode to avoid blocking:
AI: upload_file(server_id="prod", local_path="big.tar.gz", remote_path="/data/", async_transfer=true)
β "Background upload started: tf_1"
AI: transfer_status("tf_1")
β "π Uploading: 638.2 MB / 1.2 GB (53.2%) β 12.4 MB/s, ETA 46s"
AI: transfer_status("tf_1")
β "β
Upload complete: 1.2 GB, 98s, 12.3 MB/s"
Small files use synchronous mode by default β no config needed.
Connection Examples
Password authentication
AI: add_server(server_id="prod", name="Production", host="10.0.0.1", username="deploy", password="***")
AI: execute(server_id="prod", command="systemctl status nginx")
Private key authentication
AI: add_server(server_id="aws", name="AWS EC2", host="ec2-xx.compute.amazonaws.com", username="ubuntu", private_key="~/.ssh/id_rsa")
Quick connect (no config saved)
AI: quick_connect(host="192.168.1.100", username="root", password="***")
β server_id="192.168.1.100:22"
AI: execute(server_id="192.168.1.100:22", command="df -h")
AI: disconnect(server_id="192.168.1.100:22")
Via SOCKS5 proxy
AI: add_proxy(proxy_id="tunnel", name="SSH Tunnel", host="127.0.0.1", port=1080, type="5")
AI: add_server(server_id="internal", ..., proxy="tunnel")
Via jump host
AI: add_server(server_id="bastion", name="Bastion", host="bastion.example.com", username="admin", private_key="~/.ssh/id_rsa")
AI: add_server(server_id="internal", name="Internal DB", host="10.0.0.5", username="dbadmin", password="***", jump_host="bastion")
Config Location
Server and proxy configurations are stored in:
~/.ssh-mcp/config.json
Passwords are stored in plaintext. For production use, prefer private key authentication.
Requirements
- Node.js >= 18
- An MCP-compatible client (Claude Code, Claude Desktop, Cursor, etc.)
- Remote server with SSH access
License
MIT
