Skip to content
AI Security

Interview question · Identity, OAuth & Access Control

How should an MCP server authenticate and authorise its callers?

An MCP server is an API that a model drives. The scored answer treats it as an OAuth resource server, authorises every tool call against the user, and keeps upstream credentials out of the client's hands.

hardNewPreparation tags: Anthropic, Microsoft, GoogleUpdated Nov 2026

An MCP server is an API that a model drives. The scored answer treats it as an OAuth resource server, authorises every tool call against the user, and keeps upstream credentials out of the client's hands.

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 6 follow-ups like an interviewer would

You are building a remote MCP server that exposes tools over a company's data to AI clients used by employees and contractors.

  1. What role does the MCP server play in OAuth?
  2. What must the server validate on each token?
  3. Is a valid token enough to call any tool?
  4. What if a tool needs to call an upstream API?
  5. How do local MCP servers differ?
  6. How would you design authorisation for the server?

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 do you inventory and govern service accounts, API keys and AI agent identities?Next in this trackWhat does zero trust mean in practice, beyond the slogan?Next in this trackWhen should authorisation move out of application code into a central policy engine or service, and what are the trade-offs?
DISCUSSION · 0

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