SSH — policy-gated remote access runs on your own machine — the client starts it, so there is no endpoint to ping. 5 023 installs a week from npm. Last commit 14 Oct 2026.
Policy-gated, audited SSH for Linux and Windows hosts: roles, approvals, and an audit log.
We read the source, 1 d ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
* lie. `find /var/www -delete` removes a directory tree and `find / -exec sudo * id +` runs a command as root, and both classified `read-only` — the `-exec …
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ssh-mcp -- npx -y ssh-mcp
{
"mcpServers": {
"ssh-mcp": {
"args": [
"-y",
"ssh-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.ssh-mcp]
command = "npx"
args = ["-y", "ssh-mcp"]
{
"mcpServers": {
"ssh-mcp": {
"args": [
"-y",
"ssh-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"ssh-mcp": {
"args": [
"-y",
"ssh-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SSH_MCP_PASSWORD (Password for the configured profile; a per-profile SSH_MCP_<PROFILE>_PASSWORD takes precedence. Credentials are never accepted as CLI arguments.), SSH_MCP_KEY (Path to the private key file to authenticate with — the path, not the key material. A per-profile SSH_MCP_<PROFILE>_KEY takes precedence.), SSH_MCP_PASSPHRASE (Passphrase for an encrypted private key.), SSH_MCP_SUDO_PASSWORD (Password the sudo tool escalates with, when the policy in force allows the privileged class.).
The author declared them in the registry entry; get the values from the project itself.
Cordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals.
MCP gateway for controlled SSH access with per-client auth, command policies, and audit logging.
Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.
Remote MCP security gateway for auth, redaction, policy enforcement, and audit logging.
Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.
Governed email for AI agents (Mailbuttons / mbag.ai): sandbox inboxes, policy gate, audit log.
Human approvals, autonomy limits and a chained audit log for the AI agents of service firms.
OAuth 2.1 short-link tools for AI agents with scoped tokens, approvals, audit logs, and revocation.
Answers built from our own checks of this server.