Searches Hacker News stories by keyword via the public Algolia HN API and returns summaries ranked by Algolia relevance/popularity, not exact phrase matching or HN front-page order. ${PUBLIC_HN_BEHAVIOR} Empty queries are rejected, no-match searches return an empty stories array, and this is the ...
AI agents call search_stories to retrieve information from Universal Mcp Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query against a public API (Algolia HN). It retrieves and returns information about Hacker News stories based on keyword search. There are no write, delete, execute, or financial operations. The only data returned are search results and summaries. The severity is low because it queries public data with no blast radius for misuse - an AI agent cannot cause harm by searching news stories.
From the tool's definition The tool "searches Hacker News stories by keyword via the public Algolia HN API and returns summaries" - this is explicitly a search/query operation that retrieves data without modification.
Attacks that exploit this kind of access
Searches Hacker News stories by keyword via the public Algolia HN API and returns summaries ranked by Algolia relevance/popularity, not exact phrase matching or HN front-page order. ${PUBLIC_HN_BEHAVIOR} Empty queries are rejected, no-match searches return an empty stories array, and this is the right tool for topics or phrases; use story-list tools for rankings and get_item_thread for comments on a known item. It is categorised as a Read tool in the Universal Mcp Toolkit MCP Server, which means it retrieves data without modifying state.
Register the Universal Mcp Toolkit MCP server in PolicyLayer and add a rule for search_stories: 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 Universal Mcp Toolkit. Nothing to install.
search_stories 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 search_stories 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 search_stories. 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.
search_stories is provided by the Universal Mcp Toolkit MCP server (markgatcha/universal-mcp-toolkit). 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 →