Fetch personalized, strategically-relevant news for a founder. Checks cache freshness first — returns stored articles if <24h old. Otherwise scrapes Google News via Apify, ranks by cosine similarity, summarizes with Groq, and stores results.
AI agents call fetch_personalized_news to retrieve information from Founder Intelligence Engine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although the tool performs scraping and makes external HTTP requests to Google News via Apify, the net effect is retrieval and aggregation of publicly available information. The caching mechanism stores results but does not destructively alter external systems. The primary action exposed to an AI agent is fetching news, which is a Read operation.
From the tool's definition Tool 'fetches' news and 'returns stored articles', which are retrieval operations. The internal process involves 'scrapes Google News', 'ranks by cosine similarity', and 'summarizes', all of which are data processing and analysis steps without modification or…
Attacks that exploit this kind of access
Fetch personalized, strategically-relevant news for a founder. Checks cache freshness first — returns stored articles if <24h old. Otherwise scrapes Google News via Apify, ranks by cosine similarity, summarizes with Groq, and stores results. It is categorised as a Read tool in the Founder Intelligence Engine MCP Server, which means it retrieves data without modifying state.
Register the Founder Intelligence Engine MCP server in PolicyLayer and add a rule for fetch_personalized_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 Founder Intelligence Engine. Nothing to install.
fetch_personalized_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 fetch_personalized_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 fetch_personalized_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.
fetch_personalized_news is provided by the Founder Intelligence Engine MCP server (praveenkumarkunchala2005/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 →