AI agents call metasploit_search to retrieve information from Kali without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read/search operation against the Metasploit module database, returning information about available exploits, payloads, and modules. It does not execute any exploit or run any code. However, the context of a penetration testing server and the information returned (exploit details, payloads) could facilitate subsequent attacks, raising the severity to medium despite being a read operation.
From the tool's definition 'Search Metasploit database for exploits, payloads, or modules' — the tool queries/searches the Metasploit database without executing any exploit or payload
Attacks that exploit this kind of access
Search Metasploit database for exploits, payloads, or modules. It is categorised as a Read tool in the Kali MCP Server, which means it retrieves data without modifying state.
Register the Kali MCP server in PolicyLayer and add a rule for metasploit_search: 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 Kali. Nothing to install.
metasploit_search 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 metasploit_search 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 metasploit_search. 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.
metasploit_search is provided by the Kali MCP server (rangta10/kali-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →