Urgent.News

What's breaking now, across thousands of outlets.

More in AI

Your Agent Has Tools Now: Why MCP Tool Calls Need Runtime Verification

For most of the short history of LLM applications, model risk was text risk. A model could output bad advice, leak something from its prompt, or produce a convincing phishing draft — but it couldn't…

  • Tool calls expand LLM attack surface from text to actions with actual credentials
  • Runtime verification necessary to evaluate every tool call before execution

More from Wednesday 2 September →