get_category_feed
AI agents call get_category_feed to retrieve information from Google News MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries news data from Google News RSS feeds filtered by category. There are no side effects, modifications, deletions, or external operations triggered. It is purely a data retrieval operation with no risk of unintended consequences beyond accessing public news content.
From the tool's definition Tool name 'get_category_feed' and server description indicate fetching news from Google News RSS feeds by category. Server explicitly states 'Enables AI assistants to fetch real-time news' and lists 'categories' as a supported feature.
Attacks that exploit this kind of access
get_category_feed. It is categorised as a Read tool in the Google News MCP MCP Server, which means it retrieves data without modifying state.
Register the Google News MCP server in PolicyLayer and add a rule for get_category_feed: 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 MCP. Nothing to install.
get_category_feed 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_category_feed 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_category_feed. 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_category_feed is provided by the Google News MCP server (moltrus/google-news-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 →