CCAR-F Tool Design and MCP Integration Practice Question
An architect is designing an MCP server that exposes a tool to query a customer relationship management (CRM) system. The CRM API enforces per-tenant rate limits and returns HTTP 429 with a Retry-After header when exceeded. The architect wants the tool to behave predictably under load without the model having to reason about throttling. Which approach should the architect implement?
⚠ Common exam trap
The trap here is assuming the model should interpret transport errors and decide when to retry, when retry policy belongs inside the MCP server.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Implement server-side retry with exponential backoff and jitter that honors the Retry-After header, and surface a structured success or failure result to the model.
Rate-limit handling is an integration concern that should be encapsulated in the MCP server so the model never has to reason about HTTP 429 responses or timing. Honoring Retry-After with exponential backoff and jitter prevents synchronized retries and respects the upstream contract. The model then receives a normalized result it can act on, keeping tool behavior predictable under load.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Cache every CRM response indefinitely and serve cached data whenever the API returns 429.
Why it's wrong here
Indefinite caching would return stale CRM records, which is unacceptable for account status or contact data that changes frequently. It also silently masks upstream failures instead of resolving them. Caching can be part of a broader strategy, but it must be bounded by a short TTL and must not be the sole response to a 429.
- ✗
Return the raw HTTP 429 response body to the model and instruct it in the tool description to retry after a delay.
Why it's wrong here
Returning the raw 429 body pushes throttling decisions onto the model, which has no reliable clock and may retry immediately or in the wrong order. It also exposes transport-level details that are irrelevant to the task, increasing token usage and the chance of malformed follow-up calls. Rate-limit handling belongs in the server, not in the model's reasoning loop.
- ✓
Implement server-side retry with exponential backoff and jitter that honors the Retry-After header, and surface a structured success or failure result to the model.
Why this is correct
Handling retries inside the MCP server keeps throttling invisible to the model, honors the server-advertised Retry-After value, and uses jitter to avoid synchronized retry storms across tenants. The model receives a clean result envelope and can focus on the user's task. This is the standard pattern for integrating rate-limited upstream APIs behind a tool.
- ✗
Configure the MCP client to automatically retry the tool call a fixed number of times without any server-side logic.
Why it's wrong here
Client-side retries without server logic ignore the Retry-After header and can amplify load during an outage, worsening the rate-limit condition. The MCP client also lacks visibility into which upstream call failed. Retry policy that depends on upstream semantics belongs in the server that owns the API integration.
About these practice questions
Courseiva writes every CCAR-F question from scratch — 271 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Anthropic exam blueprint
This CCAR-F practice question is part of Courseiva's free Anthropic certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the CCAR-F exam.