Check a specific package for vulnerabilities
AI agents call check_vulnerability to retrieve information from Npmplus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries vulnerability data about packages without creating, modifying, deleting, or executing anything. It functions as a security scanner that reports findings. While the information could inform risky decisions, the tool itself has no side effects on packages or systems. Severity is low because misuse (e.g., checking a benign package) causes no harm.
From the tool's definition Tool performs security auditing and vulnerability checking, which is a query operation. The verb 'check' indicates inspection without modification. Description states it checks 'for vulnerabilities' - a read-only assessment of package security status.
Documented attack patterns abuse exactly the kind of access check_vulnerability gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Npmplus, and nothing reaches the server without passing your rules. This is the rule we recommend for check_vulnerability:
{
"version": "1",
"default": "deny",
"tools": {
"check_vulnerability": {}
}
}check_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.
Check a specific package for vulnerabilities. It is categorised as a Read tool in the Npmplus MCP Server, which means it retrieves data without modifying state.
Register the Npmplus MCP server in PolicyLayer and add a rule for check_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 Npmplus. Nothing to install.
check_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 check_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 check_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.
check_vulnerability is provided by the Npmplus MCP server (shacharsol/js-package-manager-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Npmplus, 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.
16 Npmplus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.