Inicializar un nuevo proyecto npm
AI agents use npm_init to create or update resources in NPM MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your NPM MCP Server environment.
npm_init creates a new project structure (package.json and related files) in the filesystem. This is a Write operation as it creates new files/directories. It is reversible in the sense that the created files can be deleted, but the primary action is creation. Severity is medium because it modifies the filesystem and could overwrite an existing package.json if run in a directory that already has one.
From the tool's definition Inicializar un nuevo proyecto npm (Initialize a new npm project)
Attacks that exploit this kind of access
Inicializar un nuevo proyecto npm. It is categorised as a Write tool in the NPM MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the NPM MCP Server MCP server in PolicyLayer and add a rule for npm_init: 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_init is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the npm_init 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_init. 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_init 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 →