AI agents invoke createTunnel to trigger actions in Mcp Ssh. 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.
Creating an SSH tunnel establishes an active network port-forwarding connection that routes traffic between hosts. This is an Execute-category action — it triggers an external network operation whose effects depend on arguments (local/remote ports, hosts). Misuse could expose internal services or bypass network security controls, making the blast radius high.
From the tool's definition Creates an SSH tunnel (port forwarding)
Documented attack patterns abuse exactly the kind of access createTunnel gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ssh, and nothing reaches the server without passing your rules. This is the rule we recommend for createTunnel:
{
"version": "1",
"default": "deny",
"tools": {
"createTunnel": {
"limits": [
{
"counter": "createtunnel_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}createTunnel 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.
Creates an SSH tunnel (port forwarding). It is categorised as a Execute tool in the Mcp Ssh MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Ssh MCP server in PolicyLayer and add a rule for createTunnel: 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 Mcp Ssh. Nothing to install.
createTunnel 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 createTunnel 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 createTunnel. 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.
createTunnel is provided by the Mcp Ssh MCP server (shuakami/mcp-ssh). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 23 Mcp Ssh tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
23 Mcp Ssh tools catalogued and risk-classified — across an index of 42,500+ MCP servers.