ssh_trust_host · Unlimited MCP: Risk & Policy

WHAT IT DOES

What ssh_trust_host does on Unlimited

AI agents invoke ssh_trust_host to trigger actions in Unlimited. 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_trust_host needs a policy

Trusting an SSH host modifies the SSH known_hosts configuration, which is a security-sensitive operation that enables future connections to that host. This is at minimum a Write operation modifying system security configuration, but since it involves establishing trust for external connections and could be exploited to MITM attacks, it warrants Execute severity. The empty description lowers confidence significantly.

From the tool's definition Tool name 'ssh_trust_host' and sibling tool 'add_host' suggest this adds an SSH host to known_hosts or trusted hosts list, triggering an external security operation. Description is empty.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ssh_trust_host Rate-limited

ssh_trust_host 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_trust_host": {
      "limits": [
        {
          "counter": "ssh_trust_host_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 Unlimited, so you can run agents against it safely.

FAQ

Questions about ssh_trust_host

What does the ssh_trust_host tool do? +

ssh_trust_host. It is categorised as a Execute tool in the Unlimited 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_trust_host? +

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

What risk level is ssh_trust_host? +

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

Can I rate-limit ssh_trust_host? +

Yes. Add a rate_limit block to the ssh_trust_host 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_trust_host completely? +

Set action: deny in the PolicyLayer policy for ssh_trust_host. 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_trust_host? +

ssh_trust_host is provided by the Unlimited MCP server (triumsebas/unlimited-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.