ssh_connect · Claude Ssh MCP: Risk & Policy

WHAT IT DOES

What ssh_connect does on Claude Ssh

AI agents invoke ssh_connect to trigger actions in Claude 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.

WHY IT NEEDS A POLICY

Why ssh_connect needs a policy

Establishing an SSH connection initiates an external network session to a remote server. While not purely destructive, this enables all subsequent Execute/Destructive operations on remote systems, making it a gateway with high blast radius. The connection itself is an external operation with significant side effects (network session, credential exposure, persistent session storage).

From the tool's definition Connect to a remote server via SSH... it will be saved for next time... reconnect to a previously saved server

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ssh_connect Rate-limited

ssh_connect 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_connect": {
      "limits": [
        {
          "counter": "ssh_connect_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 Claude Ssh, so you can run agents against it safely.

FAQ

Questions about ssh_connect

What does the ssh_connect tool do? +

Connect to a remote server via SSH. Provide full details for a new server (it will be saved for next time), or just the sessionName to reconnect to a previously saved server. It is categorised as a Execute tool in the Claude Ssh 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_connect? +

Register the Claude Ssh MCP server in PolicyLayer and add a rule for ssh_connect: 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 Claude Ssh. Nothing to install.

What risk level is ssh_connect? +

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

Can I rate-limit ssh_connect? +

Yes. Add a rate_limit block to the ssh_connect 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_connect completely? +

Set action: deny in the PolicyLayer policy for ssh_connect. 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_connect? +

ssh_connect is provided by the Claude Ssh MCP server (marabank/mcp-ssh-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.