get_geo_feed
AI agents call get_geo_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 news data based on geographic parameters with no modification, deletion, or execution capabilities. It has no financial impact and no side effects beyond returning data. The blast radius is minimal—misuse would result in retrieving unwanted news articles, not data manipulation or external operations.
From the tool's definition The tool is part of a news aggregation server that 'fetch[es] real-time news' with 'location-based queries'. The name 'get_geo_feed' and server context indicate it retrieves geographically-filtered news content.
Attacks that exploit this kind of access
get_geo_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_geo_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_geo_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_geo_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_geo_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_geo_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 →