Skip to content
AI Security

Interview question · Agent, Tool & MCP Security

What can an agent gateway or MCP gateway enforce between agents and their tools, and what can it never see?

A gateway is the one place every tool call passes, which makes it the natural home for policy. It is also blind to everything that does not pass through it, and that is the half of the answer most candidates skip.

hardNewPreparation tags: Amazon, Microsoft, CloudflareUpdated Nov 2026

A gateway is the one place every tool call passes, which makes it the natural home for policy. It is also blind to everything that does not pass through it, and that is the half of the answer most candidates skip.

Make your first attempt

What would you say before reading the answer?

  1. 01 State the assumptions your answer depends on.
  2. 02 Explain the mechanism and choose a control.
  3. 03 Name a condition that would change your decision.

The worked answer includes an approach, scoring criteria and follow-up questions. Compare the reasoning with your own.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 529 remaining answers · $25

Every worked answer in all 17 topics, every lesson in every course, the full concept curriculum, the complete practice-test bank, and the downloadable security field guides.

6 months · One payment · No auto-renewal

What if · the follow-ups in this answer

The answer works through 5 follow-ups like an interviewer would

A company routes all its agents' MCP traffic through a new gateway with per-agent tool allowlists. A week later, an agent emailed a customer list to an outside address using a script it wrote and ran in its code-execution sandbox.

  1. How did the action avoid the gateway?
  2. What closes that path?
  3. What if the email tool's server changes its description to ask agents to copy an extra address?
  4. The call passes every rule but sends the wrong document. Whose control was that?
  5. What does the complete design include?

Each rung has a nudge, a model answer, the principle that carries over and the weak answer to avoid. Premium opens every answer and ladder.

UP NEXT ON YOUR JOURNEY
Next in this trackHow would you protect AI agents at runtime: sandboxes, syscall monitoring, tool-call policy and data provenance?Next in this trackYour agent will call other companies' agents over the A2A protocol. What are the security risks, and what does a signed Agent Card prove?Next in this trackWhen an AI agent buys things for users, how do payment protocols prove consent, cap spending and let merchants trust the agent?
DISCUSSION · 0

No comments yet. Share a correction or a different way to answer it.