Instalar paquetes usando npm
AI agents invoke npm_install to trigger actions in NPM MCP 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.
Installing npm packages executes lifecycle scripts (preinstall, postinstall, etc.) from external sources, which can run arbitrary code. It also modifies the filesystem by writing to node_modules. This goes beyond a simple write operation because untrusted code may execute during installation, making Execute the most appropriate and severe category here.
From the tool's definition 'Instalar paquetes usando npm' — installs npm packages, triggering external network operations, running install scripts, and modifying the local environment
Attacks that exploit this kind of access
Instalar paquetes usando npm. It is categorised as a Execute tool in the NPM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the NPM MCP Server MCP server in PolicyLayer and add a rule for npm_install: 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_install 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 npm_install 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_install. 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_install 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 →