AI agents call npm_package_readme 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 and returns static documentation (README content) from npm packages. It has no side effects and does not modify data, making it a Read operation. Severity is low because README content is public information with no security-sensitive operations or blast radius if misused by an AI agent.
From the tool's definition Tool name is 'npm_package_readme' and description states it 'Get the README content of an npm package.' This retrieves package documentation without creating, modifying, or deleting anything.
Attacks that exploit this kind of access
Get the README content of an npm package. Returns the package. 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_package_readme: 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_package_readme 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_package_readme 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_package_readme. 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_package_readme 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 →