AI agents invoke stop_ssh_tunnel to trigger actions in Pentester-MCP. 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.
While not destructive (the tunnel can be restarted), this is an Execute action because it triggers termination of an active external process. The severity is medium rather than high because stopping a tunnel is typically reversible (can be restarted), but it could disrupt legitimate network operations or security assessments if misused by an AI agent without proper context.
From the tool's definition Terminates a background SSH tunnel or process. This involves stopping a running process/service, which is an external operation with side effects depending on which tunnel/process is targeted.
Documented attack patterns abuse exactly the kind of access stop_ssh_tunnel gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pentester-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_ssh_tunnel:
{
"version": "1",
"default": "deny",
"tools": {
"stop_ssh_tunnel": {
"limits": [
{
"counter": "stop_ssh_tunnel_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stop_ssh_tunnel 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.
Terminates a background SSH tunnel or process. It is categorised as a Execute tool in the Pentester-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pentester- MCP server in PolicyLayer and add a rule for stop_ssh_tunnel: 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 Pentester-MCP. Nothing to install.
stop_ssh_tunnel 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 stop_ssh_tunnel 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 stop_ssh_tunnel. 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.
stop_ssh_tunnel is provided by the Pentester- MCP server (halilkirazkaya/pentester-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pentester-MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
337 Pentester-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.