Search recent news using DuckDuckGo. Free tier: 50 calls.
AI agents call search_news to retrieve information from Search Proxy MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries an external news service and returns results without creating, modifying, or deleting any data. It has no side effects beyond retrieving information. The 50-call rate limit suggests it is a simple information retrieval endpoint.
From the tool's definition Tool performs a 'Search' operation that retrieves news data via DuckDuckGo. The description indicates this is a read-only operation: 'Search recent news'. No modification, deletion, execution, or financial operations are possible.
Attacks that exploit this kind of access
Search recent news using DuckDuckGo. Free tier: 50 calls. It is categorised as a Read tool in the Search Proxy MCP MCP Server, which means it retrieves data without modifying state.
Register the Search Proxy MCP server in PolicyLayer and add a rule for search_news: 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 Search Proxy MCP. Nothing to install.
search_news 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 search_news 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 search_news. 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.
search_news is provided by the Search Proxy MCP server (rumblingb/search-proxy-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 →