Retrieve Show HN posts (projects shared with the HN community), sorted by date descending.
AI agents call get_show_hn to retrieve information from HackerNews MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves publicly available Hacker News 'Show HN' posts sorted by date. It performs a query operation with no side effects, data modification, code execution, or financial implications. The only risk is potential information disclosure of public data, which is minimal and already openly accessible via the Hacker News website.
From the tool's definition Tool name 'get_show_hn' and description 'Retrieve Show HN posts' indicate data retrieval with no modification capability.
Attacks that exploit this kind of access
Retrieve Show HN posts (projects shared with the HN community), sorted by date descending. It is categorised as a Read tool in the HackerNews MCP Server MCP Server, which means it retrieves data without modifying state.
Register the HackerNews MCP Server MCP server in PolicyLayer and add a rule for get_show_hn: 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 HackerNews MCP Server. Nothing to install.
get_show_hn 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 get_show_hn 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 get_show_hn. 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.
get_show_hn is provided by the HackerNews MCP Server MCP server (sam3690/hackernews_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 →