code_vuln
AI agents call code_vuln to retrieve information from Oracle-42 DarkIntel MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the name alone, this appears to be a read operation that queries vulnerability data (consistent with a threat intelligence platform's function). The empty description limits confidence.
From the tool's definition Tool name 'code_vuln' suggests code vulnerability lookup or query. No description provided to clarify scope or capabilities.
Attacks that exploit this kind of access
code_vuln. It is categorised as a Read tool in the Oracle-42 DarkIntel MCP MCP Server, which means it retrieves data without modifying state.
Register the Oracle-42 DarkIntel MCP server in PolicyLayer and add a rule for code_vuln: 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 Oracle-42 DarkIntel MCP. Nothing to install.
code_vuln 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 code_vuln 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 code_vuln. 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.
code_vuln is provided by the Oracle-42 DarkIntel MCP server (mintmas/oracle42-darkintel-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 →