CCAR-F Tool Design and MCP Integration Practice Question
The Model Context Protocol (MCP) defines three primary primitives that servers can expose to clients. Which THREE of the following are the core primitives of MCP?
⚠ Common exam trap
Candidates frequently confuse MCP primitives with general LLM concepts like 'History' or 'Memory', missing the specific technical definitions of Resources, Tools, and Prompts defined by the protocol.
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
✓
Resources: Read-only data sources such as files, database tables, or API responses.
MCP is built on a small set of powerful primitives that allow for standardized data and capability exchange. Understanding these three components—Resources, Tools, and Prompts—is essential for any architect designing MCP-compliant systems. Each primitive serves a distinct purpose in providing context, capabilities, and reusable interaction patterns to the model.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Resources: Read-only data sources such as files, database tables, or API responses.
Why this is correct
Resources in MCP are designed to provide the model with background context or data that it can read. They represent the 'knowledge' side of the protocol, allowing the host to pull in relevant information from various external sources to ground the model's responses in factual data.
- ✓
Tools: Executable functions that allow the model to perform actions and interact with external systems.
Why this is correct
Tools are the active component of MCP, enabling the model to change the state of the world or fetch dynamic information. They are defined by JSON schemas and allow the model to perform tasks like searching the web, writing files, or calling internal business APIs.
- ✓
Prompts: Pre-defined templates that guide the model's behavior or provide reusable conversation starters.
Why this is correct
Prompts in MCP serve as reusable templates that can help users interact with the model more effectively. They allow servers to provide 'best practice' instructions or structured workflows that are optimized for the specific tools and resources the server provides to the host.
- ✗
Workflows: Sequential chains of tool calls managed automatically by the MCP server without host intervention.
Why it's wrong here
MCP does not currently define 'Workflows' as a core primitive. While a host might implement workflows using MCP tools and resources, the protocol itself focuses on the fundamental building blocks of communication rather than the higher-level orchestration of multi-step autonomous tasks within the server.
- ✗
Models: The specific LLM versions that are hosted directly within the MCP server for local processing.
Why it's wrong here
MCP is a protocol for connecting models to data and tools; it does not define the models themselves as a primitive of the server. The model typically resides with the host or a separate provider, and MCP facilitates the model's interaction with the external environment.
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.