Desinstalar paquetes usando npm
AI agents call npm_uninstall to permanently remove resources in NPM MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
npm_uninstall removes dependencies from a project, which is an irreversible operation that breaks the project state. Unlike npm_install (Write) which adds packages, uninstall permanently deletes them and their metadata. The high severity reflects that an agent uninstalling critical dependencies could render a project non-functional.
From the tool's definition Tool name 'npm_uninstall' combined with description 'Desinstalar paquetes usando npm' (Uninstall packages using npm) indicates removal of dependencies.
Attacks that exploit this kind of access
Desinstalar paquetes usando npm. It is categorised as a Destructive tool in the NPM MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the NPM MCP Server MCP server in PolicyLayer and add a rule for npm_uninstall: 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 NPM MCP Server. Nothing to install.
npm_uninstall is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the npm_uninstall 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 npm_uninstall. 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.
npm_uninstall is provided by the NPM MCP Server MCP server (kpangaa/npm-mcp-server). 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 →