AI agents call search_vulnerability_results to retrieve information from Red-team-mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name suggests searching through already-obtained vulnerability results rather than initiating new scans or executing exploits. This is a Read operation—retrieving information without direct side effects. However, confidence is moderate (0.75) because the description is empty, leaving ambiguity about whether this tool might also trigger new scans or export data in ways that could enable further attacks.
From the tool's definition Tool name 'search_vulnerability_results' indicates querying/retrieving data from prior vulnerability scans. The server context involves red teaming activities including vulnerability scanning (enumerate_vulnerabilities, get_finished_scan_results).
Documented attack patterns abuse exactly the kind of access search_vulnerability_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 search_vulnerability_results:
{
"version": "1",
"default": "deny",
"tools": {
"search_vulnerability_results": {}
}
}search_vulnerability_results is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
search_vulnerability_results. It is categorised as a Read tool in the Red-team-mcp MCP Server, which means it retrieves data without modifying state.
Register the Red-team- MCP server in PolicyLayer and add a rule for search_vulnerability_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.
search_vulnerability_results is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_vulnerability_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 search_vulnerability_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.
search_vulnerability_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.