get_news_by_topic
AI agents call get_news_by_topic to retrieve information from Google News Trends without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries news data by topic, returning articles and trends without side effects. The empty description and similar sibling tools confirm read-only retrieval semantics. Blast radius is minimal: worst case is exposure of public news data already available through Google News.
From the tool's definition Tool name 'get_news_by_keyword' and sibling tools (get_news_by_location, get_top_news, get_trending_terms) are retrieval operations.
Attacks that exploit this kind of access
get_news_by_topic. It is categorised as a Read tool in the Google News Trends MCP Server, which means it retrieves data without modifying state.
Register the Google News Trends MCP server in PolicyLayer and add a rule for get_news_by_topic: 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 Google News Trends. Nothing to install.
get_news_by_topic 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_news_by_topic 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_news_by_topic. 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_news_by_topic is provided by the Google News Trends MCP server (jmanek/google-news-trends-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 →