AI agents call news.hn-top 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.
This tool queries and retrieves public Hacker News data in multiple feed varieties (top, new, best, ask, show, job). It performs a straightforward data fetch with no capability to create, modify, delete, execute code, or move funds. The only input is the feed kind selector, which cannot influence destructive outcomes.
From the tool's definition Tool returns items with title, URL, score, comment count, author, time, dead/deleted flags from Hacker News feed—a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Hacker News feed. kind = top | new | best | ask | show | job. Returns items with title, URL, score, comment count, author, time, dead/deleted flags. 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 news.hn-top: 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.
news.hn-top 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 news.hn-top 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 news.hn-top. 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.
news.hn-top 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 →