AI agents call search_npm to retrieve information from Code Research MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search operation that queries npm's public package registry and returns results. It does not create, modify, delete, execute code, or move funds. The blast radius of misuse is minimal—an agent could only retrieve information already publicly available or spam search requests.
From the tool's definition Tool name 'search_npm' and description 'Search npm registry for JavaScript packages' indicate a query/retrieval operation with no side effects. It retrieves package information from a public registry.
Documented attack patterns abuse exactly the kind of access search_npm gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Code Research MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_npm:
{
"version": "1",
"default": "deny",
"tools": {
"search_npm": {}
}
}search_npm is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search npm registry for JavaScript packages. It is categorised as a Read tool in the Code Research MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Code Research MCP Server MCP server in PolicyLayer and add a rule for search_npm: 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 Code Research MCP Server. Nothing to install.
search_npm 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 search_npm 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 search_npm. 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.
search_npm is provided by the Code Research MCP Server MCP server (jamesjohnsdev/code-research-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Code Research MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Code Research MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.