AI-103: Developing AI Apps and Agents on Azure

By Microsoft · Question Mode

QuestionQ149

VerifiedImplement generative AI and agentic solutions

You have an agent named Agent1 that uses Model Context Protocol (MCP) calls to retrieve external data.

You need to implement guardrails so that Agent1 cannot send any content tagged as Violence to the MCP server.

Which intervention point should be used?

Explanation

A tool call intervention point evaluates the action and arguments an agent is about to send to an external tool, including the data in the request. Blocking Violence-tagged content there prevents that content from being transmitted to the MCP server before the call executes.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!