Let AI manage your remote servers. A Model Context Protocol (MCP) server that gives AI assistants full SSH access — execute commands, transfer files, manage multiple servers simultaneously, all through natural conversation.
You: "Deploy the latest build to production server"
AI: connects → uploads build → restarts service → verifies status21 Tools — Connect, execute, upload, download, write files, and more
Connection Pool — Operate multiple servers simultaneously, each command tagged with server_id
Zero-Token File Transfer — SFTP path-based transfer, file content never enters AI context
Directory Upload — Auto tar.gz compress → upload → remote decompress (fast for many small files)
Async Transfer + Progress — Background transfer for large files with real-time progress tracking
Quick Connect — Temporary connections without saving config, returns host:port as temp ID
SOCKS4/5 Proxy — Per-connection proxy support
Jump Host — SSH ProxyJump for bastion/gateway access
Multi-Auth — Password, private key, ssh-agent, keyboard-interactive (OTP/2FA)
Related MCP server: Simple SSH MCP Server
npm install -g @nl4ever/sshmcpclaude mcp add sshmcp sshmcpEdit claude_desktop_config.json:
{
"mcpServers": {
"sshmcp": {
"command": "npx",
"args": ["-y", "@nl4ever/sshmcp"]
}
}
}Go to Settings → MCP Servers → Add:
{
"sshmcp": {
"command": "npx",
"args": ["-y", "@nl4ever/sshmcp"]
}
}Tool | Description |
| List all configured servers and active connections |
| View server config details |
| Add/update server config (password, key, agent, OTP) |
| Modify server config (only pass fields you want to change) |
| Remove a server |
| Rename a server ID |
| Manually connect (usually not needed, tools auto-connect) |
| Temporary connection, returns |
| Disconnect specific server or all connections |
| Test connectivity without affecting existing connections |
Tool | Description |
| Run shell commands on remote server (with configurable timeout) |
Tool | Description |
| Read remote file content (with optional line range) |
| Write text content to remote file |
| Upload local file to remote (supports async mode) |
| Upload directory with auto compress → transfer → decompress |
| Download remote file to local (supports async mode) |
| Download directory with remote compress → transfer → local decompress |
| Check progress of async transfers (size/speed/ETA) |
Tool | Description |
| List all SOCKS proxy presets |
| Add SOCKS4/5 proxy preset |
| Remove a proxy preset |
All operation tools take a server_id parameter. The connection pool auto-manages connections — no manual connect/disconnect needed:
AI: execute(server_id="prod", command="nginx -s reload") ← auto-connects to prod
AI: execute(server_id="dev", command="tail -f /var/log/app.log") ← auto-connects to dev, prod stays
AI: execute(server_id="prod", command="curl localhost") ← reuses prod connectionFor temporary servers, use quick_connect which returns host:port as the ID:
AI: quick_connect(host="1.2.3.4", username="root", password="***")
→ "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")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)
→ "Background upload started: tf_1"
AI: transfer_status("tf_1")
→ "🔄 Uploading: 638.2 MB / 1.2 GB (53.2%) — 12.4 MB/s, ETA 46s"
AI: transfer_status("tf_1")
→ "✅ Upload complete: 1.2 GB, 98s, 12.3 MB/s"Small files use synchronous mode by default — no config needed.
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")AI: add_server(server_id="aws", name="AWS EC2", host="ec2-xx.compute.amazonaws.com", username="ubuntu", private_key="~/.ssh/id_rsa")AI: quick_connect(host="192.168.1.100", username="root", password="***")
→ 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")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")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")Server and proxy configurations are stored in:
~/.ssh-mcp/config.jsonPasswords are stored in plaintext. For production use, prefer private key authentication.
Node.js >= 18
An MCP-compatible client (Claude Code, Claude Desktop, Cursor, etc.)
Remote server with SSH access
MIT
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Security-first WordPress MCP server. 129 tools for Claude, ChatGPT, Gemini. Free on wp.org.
MCP server for Gainium — manage trading bots, deals, and balances via AI assistants
MCP server for AI dialogue using various LLM models via AceDataCloud
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/NikolaNddTesla/ssh-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server