AI agents invoke search_exploits to trigger actions in Red-team-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.
Given the server's explicit red-teaming context and sibling tools focused on exploitation, 'search_exploits' almost certainly queries exploit databases (e.g., Metasploit, ExploitDB) to find applicable exploits for targets. Even if this is primarily a Read/search operation, the server context and tool ecosystem make it a critical-severity tool because its output directly feeds into exploitation workflows.
From the tool's definition Tool name 'search_exploits' on a red-team MCP server that explicitly enables 'Metasploit exploitation' and includes sibling tools like 'execute_exploit' and 'enumerate_vulnerabilities'
Documented attack patterns abuse exactly the kind of access search_exploits 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_exploits:
{
"version": "1",
"default": "deny",
"tools": {
"search_exploits": {
"limits": [
{
"counter": "search_exploits_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}search_exploits 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.
search_exploits. It is categorised as a Execute tool in the Red-team-mcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Red-team- MCP server in PolicyLayer and add a rule for search_exploits: 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_exploits 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 search_exploits 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_exploits. 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_exploits 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.