AI agents invoke run_graphw00f 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.
graphw00f is a GraphQL reconnaissance and fingerprinting tool that executes external probing operations against target systems. Even though the direct description is empty, the server context makes clear this tool runs autonomous penetration testing operations. The effect depends on attacker-controlled arguments (target URL, GraphQL endpoints).
From the tool's definition Tool is part of Pentester-MCP server that 'enables AI assistants to autonomously execute over 200 open-source penetration testing tools...including reconnaissance, web exploitation, and brute-forcing.' The tool name 'run_graphw00f' (GraphQL reconnaissance…
Documented attack patterns abuse exactly the kind of access run_graphw00f 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 run_graphw00f:
{
"version": "1",
"default": "deny",
"tools": {
"run_graphw00f": {
"limits": [
{
"counter": "run_graphw00f_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_graphw00f 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.
run_graphw00f. 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 run_graphw00f: 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.
run_graphw00f 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 run_graphw00f 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 run_graphw00f. 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.
run_graphw00f 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.