漏洞情报：获取公开漏洞的基础信息、风险评估、PoC、处置建议、补丁等信息
AI agents call vulnerability to retrieve information from ThreatMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves/queries existing vulnerability intelligence data from ThreatBook's API. It performs no writes, executes no code, and causes no side effects. The data returned (CVE info, PoC references, patches) is read-only threat intelligence.
From the tool's definition 获取公开漏洞的基础信息、风险评估、PoC、处置建议、补丁等信息 — 'get' (获取) public vulnerability information, risk assessments, PoC, remediation advice, and patch details
Documented attack patterns abuse exactly the kind of access vulnerability gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ThreatMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for vulnerability:
{
"version": "1",
"default": "deny",
"tools": {
"vulnerability": {}
}
}vulnerability 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.
漏洞情报：获取公开漏洞的基础信息、风险评估、PoC、处置建议、补丁等信息. It is categorised as a Read tool in the ThreatMCP MCP Server, which means it retrieves data without modifying state.
Register the Threat MCP server in PolicyLayer and add a rule for vulnerability: 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 ThreatMCP. Nothing to install.
vulnerability 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 vulnerability 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 vulnerability. 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.
vulnerability is provided by the Threat MCP server (naxg/threatmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ThreatMCP, 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.
15 ThreatMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.