MCP — How Agents Connect to Tools

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-builders-agentic-agent-mcp

1. Which sentence best captures the main idea of 'MCP — How Agents Connect to Tools'?

   1. Agents and chatbots are the same thing in every way
   2. Agents should always run without limits or oversight
   3. Tools and goals are unnecessary for agent design
   4. MCP (Model Context Protocol) is a standard way for agents to safely talk to tools.

2. Which of the following is part of 'What MCP enables'?

   1. Never log what the agent did
   2. An agent can use any MCP-compatible tool. A new tool just needs to speak MCP and any agent can use it.
   3. Skip every form of evaluation
   4. Hide tool calls from the operator

3. Which of the following is part of 'Three things MCP makes possible'?

   1. Never log what the agent did
   2. Plug-and-play tools across agents
   3. Skip every form of evaluation
   4. Disable safety checks for speed

4. Which of the following is part of 'Review date'?

   1. Always run with no oversight
   2. Use the most expensive model regardless of fit
   3. Reviewed in 2026. Treat fast-changing product names, prices, availability, and policy details as examples to verify before use.
   4. Skip every form of evaluation

5. What is 'MCP' in this context?

   1. A trick to bypass approvals
   2. A reason to skip all logging
   3. A core concept covered in MCP — How Agents Connect to Tools
   4. A way to disable the agent's tools

6. What is 'protocol' in this context?

   1. A trick to bypass approvals
   2. A way to disable the agent's tools
   3. A reason to skip all logging
   4. A core concept covered in MCP — How Agents Connect to Tools

7. What is 'interoperability' in this context?

   1. A reason to skip all logging
   2. A core concept covered in MCP — How Agents Connect to Tools
   3. A way to disable the agent's tools
   4. A trick to bypass approvals

8. What is MCP (Model Context Protocol) primarily for?

   1. Encrypting prompts only
   2. Replacing operating systems
   3. Renaming chat models
   4. A standard way to expose tools and data sources to AI clients

9. What is the best response when an agent suggests an action you do not understand?

   1. Reject everything and stop using the agent
   2. Approve it to keep things moving
   3. Run it twice to be sure
   4. Ask the agent to explain the action and its expected effect before approving

10. Which is the best way to think about an agent's 'autonomy level'?

    1. It is binary — fully autonomous or not
    2. Autonomy does not affect risk
    3. It is a slider from suggestion only, to ask-then-act, to act-then-report, to fully autonomous
    4. It depends only on the model size

11. Which of these is the strongest indicator that an agent workflow is ready to scale?

    1. It used the latest model
    2. It worked once for one user
    3. It passes a repeatable eval, has cost in budget, and a rollback plan
    4. It runs without any logging

12. Why does an AI agent need 'tools' such as a browser, calendar, or code runner?

    1. Tools let the agent take actions in the world instead of only producing text
    2. Tools make the model speak more naturally
    3. Tools replace the need for any prompts
    4. Tools shrink the context window

13. An agent that costs $0.04 per task on average will run 10,000 times this month. Roughly what should you budget?

    1. About $400
    2. About $40
    3. About $4,000
    4. About $4

14. What is the most reliable way to keep an autonomous agent from going off the rails on a long task?

    1. Set a clear goal, a step budget, and review checkpoints
    2. Run it for as many steps as possible without checking in
    3. Disable its tools so it can only think
    4. Trust the model to know when to stop

15. Which signal best tells you an agent is stuck in a runaway loop?

    1. It finishes the task in one step
    2. It asks one clarifying question
    3. It keeps repeating the same tool call with no new progress
    4. It returns a short summary and stops