hn_search
AI agents call hn_search to retrieve information from Pypi:hn Tech Signal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves or queries data from HackerNews without modifying, executing, or destructing anything. Despite the empty description, the naming convention and server context strongly indicate a read operation for searching public tech news. Low severity because search operations pose minimal risk even if misused—they only retrieve existing public information.
From the tool's definition Tool name 'hn_search' suggests searching HackerNews; sibling tools like 'hn_top_stories', 'arxiv_search', and 'lobsters_hot' are all read-only queries.
Attacks that exploit this kind of access
hn_search. It is categorised as a Read tool in the Pypi:hn Tech Signal MCP Server, which means it retrieves data without modifying state.
Register the Pypi:hn Tech Signal MCP server in PolicyLayer and add a rule for hn_search: 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 Pypi:hn Tech Signal. Nothing to install.
hn_search 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_search 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_search. 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_search is provided by the Pypi:hn Tech Signal MCP server (malkreide/hn-tech-signal-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 →