Query the NetExec database for stored credentials and hosts.
AI agents call nxc_database to retrieve information from Sec Netexec without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query operation that retrieves data from a NetExec database without modifying it, placing it in the Read category. While the action itself is non-destructive and reversible, the severity is high because: (1) it exposes stored credentials which are security-sensitive, (2) it reveals host information from a penetration testing context, and (3) an AI agent with access could exfiltrate sensitive…
From the tool's definition Tool description states 'Query the NetExec database for stored credentials and hosts.' The verb 'Query' and the read-only nature of database lookups indicate a retrieval operation.
Attacks that exploit this kind of access
Query the NetExec database for stored credentials and hosts. It is categorised as a Read tool in the Sec Netexec MCP Server, which means it retrieves data without modifying state.
Register the Sec Netexec MCP server in PolicyLayer and add a rule for nxc_database: 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 Sec Netexec. Nothing to install.
nxc_database 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 nxc_database 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 nxc_database. 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.
nxc_database is provided by the Sec Netexec MCP server (schwarztim/sec-netexec-mcp). 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 →