Run security audit with npm/yarn audit to detect vulnerabilities
AI agents invoke nodejs_security to trigger actions in MCP DevTools Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool invokes security auditing commands that query and process the dependency tree and vulnerability database. While primarily informational (read-like in intent), the execution of npm/yarn audit is a command execution that could be abused to extract information about private dependencies or trigger side effects in misconfigured environments.
From the tool's definition Tool performs 'Run security audit with npm/yarn audit' — executes an external command (npm or yarn audit) whose effects depend on the project context and dependencies analyzed.
Documented attack patterns abuse exactly the kind of access nodejs_security gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP DevTools Server, and nothing reaches the server without passing your rules. This is the rule we recommend for nodejs_security:
{
"version": "1",
"default": "deny",
"tools": {
"nodejs_security": {
"limits": [
{
"counter": "nodejs_security_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}nodejs_security stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run security audit with npm/yarn audit to detect vulnerabilities. It is categorised as a Execute tool in the MCP DevTools Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP DevTools Server MCP server in PolicyLayer and add a rule for nodejs_security: 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 MCP DevTools Server. Nothing to install.
nodejs_security is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the nodejs_security 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 nodejs_security. 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.
nodejs_security is provided by the MCP DevTools Server MCP server (rshade/mcp-devtools-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP DevTools Server, 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.
79 MCP DevTools Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.