ssh_forward · Mcpx MCP: Risk & Policy

WHAT IT DOES

What ssh_forward does on Mcpx

AI agents invoke ssh_forward to trigger actions in Mcpx. 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.

WHY IT NEEDS A POLICY

Why ssh_forward needs a policy

Port forwarding is an active network operation that opens tunnels between hosts, potentially exposing internal services to external networks or vice versa. It is not purely data retrieval or modification, but execution of a network-level action. It doesn't destroy data, but misuse could expose sensitive infrastructure, warranting high severity.

From the tool's definition "Create a port forward" — establishes network port forwarding via SSH, which triggers an external network operation whose effects depend on arguments (host, ports, direction).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ssh_forward Rate-limited

ssh_forward 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ssh_forward": {
      "limits": [
        {
          "counter": "ssh_forward_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mcpx, so you can run agents against it safely.

FAQ

Questions about ssh_forward

What does the ssh_forward tool do? +

Create a port forward. It is categorised as a Execute tool in the Mcpx MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ssh_forward? +

Register the Mcpx MCP server in PolicyLayer and add a rule for ssh_forward: 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 Mcpx. Nothing to install.

What risk level is ssh_forward? +

ssh_forward is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit ssh_forward? +

Yes. Add a rate_limit block to the ssh_forward 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.

How do I block ssh_forward completely? +

Set action: deny in the PolicyLayer policy for ssh_forward. 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.

What MCP server provides ssh_forward? +

ssh_forward is provided by the Mcpx MCP server (rmednitzer/relay-shell). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.