AI agents invoke run_medusa 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.
Medusa is a well-known parallel network login brute-force tool used in penetration testing to guess credentials against target systems. Running it constitutes executing an external tool whose effects (account compromise, denial of service, system access) depend entirely on how an AI agent configures the target host, port, username, and password wordlist.
From the tool's definition Tool name 'run_medusa' with context of a pentester MCP server designed to 'autonomously execute over 200 open-source penetration testing tools' including 'brute-forcing'. Medusa is a credential brute-force attack tool.
Documented attack patterns abuse exactly the kind of access run_medusa 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_medusa:
{
"version": "1",
"default": "deny",
"tools": {
"run_medusa": {
"limits": [
{
"counter": "run_medusa_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_medusa 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_medusa. 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_medusa: 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_medusa 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_medusa 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_medusa. 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_medusa 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.