AI agents invoke ssh_tunnel_start to trigger actions in SSH MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
SSH tunnel creation is an Execute action because it actively initiates a network operation with externally visible effects (opening ports, establishing connections). The tool's impact depends on what services are being exposed and how the tunnel is configured—an AI agent could misuse it to expose internal services, create backdoors, or pivot to other systems on the network.
From the tool's definition Tool description states 'Start an SSH tunnel for port forwarding' which initiates a network tunnel—an active operation that establishes and maintains a persistent connection to forward traffic between local and remote ports.
Documented attack patterns abuse exactly the kind of access ssh_tunnel_start gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SSH MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for ssh_tunnel_start:
{
"version": "1",
"default": "deny",
"tools": {
"ssh_tunnel_start": {
"limits": [
{
"counter": "ssh_tunnel_start_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}ssh_tunnel_start stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Start an SSH tunnel for port forwarding. It is categorised as a Execute tool in the SSH MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SSH MCP Server MCP server in PolicyLayer and add a rule for ssh_tunnel_start: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches SSH MCP Server. Nothing to install.
ssh_tunnel_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ssh_tunnel_start rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for ssh_tunnel_start. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
ssh_tunnel_start is provided by the SSH MCP Server MCP server (kinothe-kafkaesque/ssh-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SSH MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
15 SSH MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.