Scrape news from configured sources
AI agents call scrape_news to retrieve information from News Instagram MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Scraping news from public sources is a read-only operation. It retrieves data without creating, modifying, deleting, or executing operations. While it may have terms-of-service implications depending on the sources being scraped, from a functional security perspective it is a read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name is 'scrape_news' and description states it will 'Scrape news from configured sources' — a retrieval operation with no modification or side effects on the sources being read.
Attacks that exploit this kind of access
Scrape news from configured sources. It is categorised as a Read tool in the News Instagram MCP Server MCP Server, which means it retrieves data without modifying state.
Register the News Instagram MCP Server MCP server in PolicyLayer and add a rule for scrape_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 News Instagram MCP Server. Nothing to install.
scrape_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 scrape_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 scrape_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.
scrape_news is provided by the News Instagram MCP Server MCP server (zegh6389/news-instagram-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 →