AI agents invoke ad_relay_setup to trigger actions in pentestMCP. 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.
Given the server context (pentestMCP with Active Directory attack tools) and the naming convention matching other AD attack tools, 'ad_relay_setup' almost certainly sets up an NTLM relay attack infrastructure. This is an offensive security Execute-class operation with critical severity, as it can lead to full domain compromise by relaying captured credentials.
From the tool's definition Tool name 'ad_relay_setup' on a penetration testing MCP server alongside tools like ad_dcsync, ad_coerce_petitpotam, and ad_coerce_printerbug strongly implies NTLM relay attack setup (e.g., Responder/ntlmrelayx), which captures and relays authentication…
Documented attack patterns abuse exactly the kind of access ad_relay_setup gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and pentestMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for ad_relay_setup:
{
"version": "1",
"default": "deny",
"tools": {
"ad_relay_setup": {
"limits": [
{
"counter": "ad_relay_setup_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}ad_relay_setup 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.
ad_relay_setup. It is categorised as a Execute tool in the pentestMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the pentest MCP server in PolicyLayer and add a rule for ad_relay_setup: 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 pentestMCP. Nothing to install.
ad_relay_setup 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 ad_relay_setup 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 ad_relay_setup. 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.
ad_relay_setup is provided by the pentest MCP server (ramkansal/pentestmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 36 pentestMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
36 pentestMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.