AI agents call hn_user 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 user profile or account information from Hacker News. It performs a simple lookup query with no side effects, data modification, code execution, or destructive operations. The blast radius of misuse is minimal—an attacker could only gather publicly available user information, which is already accessible through the Hacker News website itself. This is a straightforward Read category tool.
From the tool's definition Tool name 'hn_user' and description 'Look up an HN user' indicate a query/retrieval operation. The verb 'Look up' is a read operation that retrieves user information from Hacker News without modifying or executing anything.
Attacks that exploit this kind of access
Look up an HN user. 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_user: 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_user 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_user 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_user. 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_user 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 →