AI agents use save_hacking_results to create or update resources in Red-team-mcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Red-team-mcp environment.
With an empty description, direct certainty is limited (confidence 0.65). However, the 'save_' prefix indicates data persistence/modification rather than pure retrieval or destruction. The sibling tools (port_scan, enumerate_vulnerabilities, execute_exploit) perform reconnaissance and exploitation, so this tool likely stores those results.
From the tool's definition Tool name 'save_hacking_results' from a red-team-mcp server context; description is empty. The 'save_*' pattern and presence on an offensive security server suggests storing/recording data, likely results from port scanning, vulnerability assessment, or…
Documented attack patterns abuse exactly the kind of access save_hacking_results gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Red-team-mcp, and nothing reaches the server without passing your rules. This is the rule we recommend for save_hacking_results:
{
"version": "1",
"default": "deny",
"tools": {
"save_hacking_results": {
"limits": [
{
"counter": "save_hacking_results_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_hacking_results stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
save_hacking_results. It is categorised as a Write tool in the Red-team-mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Red-team- MCP server in PolicyLayer and add a rule for save_hacking_results: 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 Red-team-mcp. Nothing to install.
save_hacking_results is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_hacking_results 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 save_hacking_results. 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.
save_hacking_results is provided by the Red-team- MCP server (skjortan23/read-team-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Red-team-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.
13 Red-team-mcp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.