fetch_content
AI agents call fetch_content 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.
The server explicitly states it 'Enables AI assistants to fetch real-time news' with features for headlines, searches, and caching. All sibling tools (get_*, list_*, decode_*) are read-only operations. Although the tool description is empty, the strong contextual evidence from server purpose and naming convention indicates fetch_content retrieves news data as a read operation with no side effects.
From the tool's definition Tool named 'fetch_content' with empty description, but exists on Google News MCP server alongside tools like 'get_category_feed', 'get_top_headlines', and 'get_search_feed'.
Attacks that exploit this kind of access
fetch_content. 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 fetch_content: 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.
fetch_content 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 fetch_content 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 fetch_content. 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.
fetch_content 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 →