get_news_by_keyword
AI agents call get_news_by_keyword 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 news articles based on keyword search. Retrieval and query operations that return data without side effects are classified as Read. The empty tool description slightly reduces confidence, but the name and server context clearly indicate a search/retrieval function with no write, execute, destructive, or financial impact.
From the tool's definition Tool name 'get_news_by_keyword' and server description state it 'Search and retrieve news articles' with no mention of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
get_news_by_keyword. 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_keyword: 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_keyword 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_keyword 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_keyword. 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_keyword 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 →