news_search
AI agents call news_search to retrieve information from You Com MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
News search is a query operation that retrieves information from news sources with no side effects or data modification. The lack of a description is noted, but the context of being on a research/search server with similarly-named sibling tools and the tool name itself (news_search) indicate read-only retrieval. Severity is low because retrieving news data has minimal blast radius even if misused by an agent.
From the tool's definition Tool name is 'news_search' and sibling tools include 'research', 'smart_search', and 'web_search' on a You.com MCP server that provides search and research capabilities. The pattern strongly indicates this retrieves news data without modification.
Attacks that exploit this kind of access
news_search. It is categorised as a Read tool in the You Com MCP Server MCP Server, which means it retrieves data without modifying state.
Register the You Com MCP Server MCP server in PolicyLayer and add a rule for news_search: 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 You Com MCP Server. Nothing to install.
news_search 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 news_search 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 news_search. 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.
news_search is provided by the You Com MCP Server MCP server (jimbul/youdotcom_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 →