mcp-remote-ssh
MCP server giving AI agents full SSH access -- persistent sessions, structured command output, SFTP file transfer, port forwarding, session transcript recording, and .
接入你的智能体
從發布者安裝。不是 PlugMCP 端點。
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
MCP server giving AI agents full SSH access -- persistent sessions, structured command output, SFTP file transfer, port forwarding, session transcript recording, and .
MCP server for remote SSH operations -- persistent sessions, structured command output, SFTP file transfer, port forwarding, and secret-safe environment variable injection with automatic output redaction.
Every other SSH MCP server is missing something: no password auth, no persistent sessions, no SFTP, no port forwarding, or no structured exit codes. This one has all of them -- plus the only MCP-level secret management that prevents AI agents from ever seeing your credentials.
The problem: When an AI agent needs to use API tokens, passwords, or keys on a remote server, the standard approach exposes secrets in the LLM's context window. The agent either reads the secret file (now it's in the conversation) or runs echo $TOKEN and sees the value in the output.
The solution: ssh_load_env_file reads secrets from a local file on your machine, injects them into the remote SSH session, and registers them for automatic output redaction. The AI agent can use the variables freely -- every tool response is scrubbed before it reaches the LLM.
# Agent calls this -- file is read from YOUR machine, not the remote host
ssh_load_env_file(session_id="abc", file_path="~/.secrets/prod.env")
→ "Loaded 3 variables from local:~/.secrets/prod.env: API_TOKEN, DB_PASS, SECRET_KEY"
# Agent tries to echo the value -- redacted automatically
ssh_execute(session_id="abc", command="echo $API_TOKEN")
→ {"stdout": "***\n", "exit_code": 0}
# Agent dumps the environment -- all secret values scrubbed
ssh_execute(session_id="abc", command="env | grep API_TOKEN")
→ {"stdout": "API_TOKEN=***\n", "exit_code": 0}
# Agent reads a file containing a secret -- also redacted
ssh_read_remote_file(session_id="abc", remote_path="/etc/app/config")
→ "db_password=***\ndb_host=localhost\n"
# Normal commands work perfectly -- no over-redaction
ssh_execute(session_id="abc", command="uname -a")
→ {"stdout": "Linux server 6.1.0 ...", "exit_code": 0}
┌─────────┐ ┌──────────────────────────────┐ ┌─────────────┐
│ LLM │ ←─JSON─ │ MCP Server (your machine) │ ──SSH─→ │ Remote Host │
│ (Agent) │ │ │ │ │
└─────────┘ │ 1. Reads ~/.secrets/prod.env│ └─────────────┘
│ 2. Parses KEY=VALUE pairs │
│ 3. Stores values in memory │
│ 4. Injects into SSH session │
│ 5. Redacts ALL tool output │
└──────────────────────────────┘
read -r VAR <<< 'value' && export VAR (no process tree exposure)ssh_execute feeds secrets via stdin to a bash wrapper, so they never appear in /proc/*/cmdlinessh_execute, ssh_shell_send, ssh_shell_read, ssh_read_remote_file) is scrubbed before reaching the LLMabc123 is replaced before abc)This server uses Paramiko's AutoAddPolicy — unknown host keys are accepted without prompting. This is intentional for QE/lab environments where hosts are ephemeral (Beaker, cloud instances, CI machines). The trade-off:
If you operate on untrusted networks, consider wrapping connections through a VPN or SSH bastion with pre-distributed host keys. A host_key_policy parameter may be added in a future release for strict environments.
Standard .env format:
# Comments are ignored
API_TOKEN=your-secret-token
DB_PASSWORD="quoted values work"
SECRET_KEY='single quotes too'
export ALSO_WORKS=yes
Recording is off by default. Enable it per session when you need an audit log of what the agent actually ran — useful for bug reproductions and test campaigns.
# Start recording on connect
ssh_connect(host="lab.example.com", username="root", password="...", record=True)
# Or toggle later
ssh_start_recording(session_id="a1b2c3d4")
ssh_execute(session_id="a1b2c3d4", command="uname -a")
ssh_get_transcript(session_id="a1b2c3d4")
→ {"recording": true, "total_entries": 2, "transcript": "[12:01:02] --- connect: lab.example.com ---\n[12:01:05] $ uname -a\nLinux ...\n[exit 0]"}
ssh_save_transcript(session_id="a1b2c3d4", path="/tmp/lab-session.log")
ssh_stop_recording(session_id="a1b2c3d4")
ssh_save_transcript or ssh_get_transcript firstuvx mcp-remote-ssh # or: pip install mcp-remote-ssh
{
"mcpServers": {
"remote-ssh": {
"command": "uvx",
"args": ["mcp-remote-ssh"]
}
}
}
ssh_connect(host="server.example.com", username="admin", password="secret", record=True)
→ {"session_id": "a1b2c3d4", "connected": true, "recording": true}
ssh_load_env_file(session_id="a1b2c3d4", file_path="~/.secrets/prod.env")
→ "Loaded 2 variables: API_TOKEN, DB_PASS"
ssh_execute(session_id="a1b2c3d4", command="curl -H \"Authorization: Bearer $API_TOKEN\" https://api.example.com")
→ {"stdout": "{\"status\": \"ok\"}", "exit_code": 0} # token used but never visible
ssh_shell_open(session_id="a1b2c3d4")
ssh_shell_send(session_id="a1b2c3d4", data="cd /opt && make -j$(nproc)")
ssh_shell_wait(session_id="a1b2c3d4", pattern="$ ", timeout=600)
ssh_upload_file(session_id="a1b2c3d4", local_path="config.yaml", remote_path="/etc/app/config.yaml")
ssh_forward_port(session_id="a1b2c3d4", remote_port=5432, local_port=15432)
ssh_execute uses exec_command() for clean structured output with real exit codesssh_execute feeds exports via stdin to a bash wrapper, then execs the actual command -- secrets never appear in the process treessh_shell_* uses invoke_shell() for persistent interactive sessionsrun_in_executor to stay asyncshell_read pollingMIT
MCP server for remote SSH operations -- persistent sessions, structured command output, SFTP file transfer, port forwarding, and secret-safe environment variable injection with automatic output redact
總覽
MCP server for remote SSH operations -- persistent sessions, structured command output, SFTP file transfer, port forwarding, and secret-safe environment variable injection with automatic output redaction.
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
MCP Remote Ssh 透過 stdio 在本機執行。
上次檢查時間:2026-10-28。 MCP server for remote SSH operations -- persistent sessions, structured command output, SFTP file transfer, port forwarding, and secret-safe environment variable injection with automatic output redaction.