search_news
AI agents call search_news to retrieve information from TrendRadar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries news data without modifying, deleting, or executing external operations. It fits the Read category as a search/query function. Severity is low because retrieving news data has no destructive blast radius. Confidence is moderate (0.85) rather than high due to empty description, but context strongly suggests a read operation.
From the tool's definition Tool name 'search_news' combined with server context (TrendRadar is a 'news assistant that aggregates trending information') and sibling tools (get_latest_news, get_news_by_date, find_similar_news, analyze_sentiment) indicate this retrieves/queries news data.
Attacks that exploit this kind of access
search_news. It is categorised as a Read tool in the TrendRadar MCP Server, which means it retrieves data without modifying state.
Register the TrendRadar MCP server in PolicyLayer and add a rule for search_news: 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 TrendRadar. Nothing to install.
search_news 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_news 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_news. 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_news is provided by the TrendRadar MCP server (yanglang116/trendradar). 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 →