AI agents call registry.npm-lookup to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and queries public npm package metadata. It does not create, modify, delete, execute code, or perform financial transactions. The 'lookup' action and the nature of returned data (metadata fields) confirm this is a Read operation with minimal risk.
From the tool's definition Tool performs a lookup operation that 'Returns description, repository, license, author + maintainers, keywords, distTags, latest version, and the 50 most recent versions with publish dates.' This is purely informational retrieval with no side effects.
Attacks that exploit this kind of access
Look up an npm package by name (supports @scope/name). Returns description, repository, license, author + maintainers, keywords, distTags, latest version, and the 50 most recent versions with publish dates. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for registry.npm-lookup: 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 Mcp. Nothing to install.
registry.npm-lookup 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 registry.npm-lookup 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 registry.npm-lookup. 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.
registry.npm-lookup is provided by the MCP server (@2sio/mcp). 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 →