AI agents call hn_top to retrieve information from Devfeed without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from Hacker News without any side effects, modification, or execution capabilities. It is a straightforward read operation that fetches the current top stories, making it a safe Read category tool with low severity risk.
From the tool's definition Tool name 'hn_top' and description 'Current top HN stories' indicates retrieval of publicly available Hacker News content with no modification or execution capability.
Attacks that exploit this kind of access
Current top HN stories. It is categorised as a Read tool in the Devfeed MCP Server, which means it retrieves data without modifying state.
Register the Devfeed MCP server in PolicyLayer and add a rule for 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 Devfeed. Nothing to install.
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 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 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.
hn_top is provided by the Devfeed MCP server (upgpt-ai/devfeed-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 →