Search the npm registry for packages matching a query. Returns a list of packages with name, version, description, keywords, and quality scores. Args: - query (string): Search query for npm packages - limit (number): Maximum results to return, 1-30 (default: 10) Returns: List of matching packages...
AI agents call npm_search to retrieve information from Npm Info without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the npm registry to retrieve package information based on search criteria. It has no side effects, does not create, modify, or delete data, and does not execute code or commands. It is a straightforward information retrieval operation that falls clearly into the Read category.
From the tool's definition Search the npm registry for packages matching a query. Returns a list of packages with name, version, description, keywords, and quality scores. No modification, deletion, or execution capabilities—purely retrieves and queries package metadata.
Attacks that exploit this kind of access
Search the npm registry for packages matching a query. Returns a list of packages with name, version, description, keywords, and quality scores. Args: - query (string): Search query for npm packages - limit (number): Maximum results to return, 1-30 (default: 10) Returns: List of matching packages with metadata and scores. Each result includes: - name, version, description, keywords - links (npm, homepage, repository) - scores (quality, popularity, maintenance, overall) Examples: -. It is categorised as a Read tool in the Npm Info MCP Server, which means it retrieves data without modifying state.
Register the Npm Info MCP server in PolicyLayer and add a rule for npm_search: 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 Info. Nothing to install.
npm_search 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_search 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_search. 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_search is provided by the Npm Info MCP server (kongyo2/npm-info). 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 →