cme_ssh · CrackMapExec MCP Server MCP: Risk & Policy

WHAT IT DOES

What cme_ssh does on CrackMapExec MCP Server

AI agents invoke cme_ssh to trigger actions in CrackMapExec 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.

WHY IT NEEDS A POLICY

Why cme_ssh needs a policy

SSH authentication and command execution constitute the Execute category—triggering external operations whose effects depend on arguments. Given the context of a penetration testing framework (CrackMapExec/NetExec) with credential support, this tool could execute arbitrary commands on remote systems with severe blast radius.

From the tool's definition The tool description explicitly states it 'Execute[s] SSH protocol operations' and supports 'authentication for Linux/Unix hosts,' enabling command execution on remote systems.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cme_ssh Rate-limited

cme_ssh 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": {
    "cme_ssh": {
      "limits": [
        {
          "counter": "cme_ssh_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 CrackMapExec MCP Server, so you can run agents against it safely.

FAQ

Questions about cme_ssh

What does the cme_ssh tool do? +

Execute SSH protocol operations. Supports password and key-based authentication for Linux/Unix hosts. It is categorised as a Execute tool in the CrackMapExec MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cme_ssh? +

Register the CrackMapExec MCP Server MCP server in PolicyLayer and add a rule for cme_ssh: 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 CrackMapExec MCP Server. Nothing to install.

What risk level is cme_ssh? +

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

Can I rate-limit cme_ssh? +

Yes. Add a rate_limit block to the cme_ssh 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 cme_ssh completely? +

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

cme_ssh is provided by the CrackMapExec MCP Server MCP server (schwarztim/sec-crackmapexec-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.