Obtener información detallada de un paquete
AI agents call npm_info to retrieve information from NPM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and displays package details (metadata, versions, dependencies, etc.) with no side effects. It does not install, modify, delete, or execute code. The context of being part of a package management server alongside audit and search tools further confirms this is a informational query tool.
From the tool's definition Tool name 'npm_info' and description 'Obtener información detallada de un paquete' (Get detailed information about a package) indicate retrieval of package metadata without modification.
Attacks that exploit this kind of access
Obtener información detallada de un paquete. It is categorised as a Read tool in the NPM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NPM MCP Server MCP server in PolicyLayer and add a rule for npm_info: 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_info 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 npm_info 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_info. 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_info 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 →