MANDATORY: call this BEFORE running npm install, yarn add, or pnpm add — whether the user asked for the package or you decided to install it yourself. Verifies the package exists (blocks hallucinated names), checks for typosquatting, runs security audit, and returns allow/warn/block. If the resul...
AI agents call depguard_guard to retrieve information from Depguard without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs pre-install checks — it queries registry data, checks for typosquatting, and runs security audits to return a recommendation. It does not itself install packages or modify any state; it reads and analyzes package metadata. However, severity is medium because a miscategorization or bypass of this gate could result in malicious packages being installed by subsequent tools.
From the tool's definition Verifies the package exists (blocks hallucinated names), checks for typosquatting, runs security audit, and returns allow/warn/block
Documented attack patterns abuse exactly the kind of access depguard_guard gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Depguard, and nothing reaches the server without passing your rules. This is the rule we recommend for depguard_guard:
{
"version": "1",
"default": "deny",
"tools": {
"depguard_guard": {}
}
}depguard_guard 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.
MANDATORY: call this BEFORE running npm install, yarn add, or pnpm add — whether the user asked for the package or you decided to install it yourself. Verifies the package exists (blocks hallucinated names), checks for typosquatting, runs security audit, and returns allow/warn/block. If the result is. It is categorised as a Read tool in the Depguard MCP Server, which means it retrieves data without modifying state.
Register the Depguard MCP server in PolicyLayer and add a rule for depguard_guard: 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 Depguard. Nothing to install.
depguard_guard 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 depguard_guard 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 depguard_guard. 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.
depguard_guard is provided by the Depguard MCP server (mopanc/depguard). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Depguard, 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.
14 Depguard tools catalogued and risk-classified — across an index of 43,000+ MCP servers.