Fresher / New Grad

Someone asks you what MCP is at a meetup. How do you explain it?

Where does the MCP client live, and why is it one to one with a server?

A local stdio MCP server has no auth token. Is that a security hole?

Why did MCP pick JSON-RPC 2.0 as its wire format instead of REST or gRPC?

GitHub ships an official MCP server. What can it do, and how does it authenticate?

The filesystem MCP server gives agents file access. How does it stop them from reading everything on disk?

How does Cursor discover and load MCP servers?

An MCP tools/call result comes back. Which content types could it contain?

You need to add an MCP server to Claude Desktop. Which file do you edit and what goes in it?

What happens during the MCP initialize handshake, and why does it matter?

Your colleague says MCP and function calling do the same thing. Where are they wrong?

A tokenizer has a 'vocabulary'. What is it, and why does its size matter for the model?

Your team debates 32K vs 128K vs 256K vocab. What is the core tradeoff they should frame?

Your input is 9,000 tokens but max_length is 8,192. What are your truncation options?

You open a HuggingFace model repo and see tokenizer_config.json. What is in it and what is NOT?

Token 1234 means 'the' in one model and garbage in another. Why?

An LLM never sees raw text. So what does it actually process?

BOS, EOS, PAD: why do tokenizers reserve these ids instead of using normal text?

Someone confuses 'sequence length' with 'context window'. How do you correct them?

You change one word in the system prompt and prompt caching breaks. Why?

Pre-tokenization splits text before BPE merges. Why is that boundary important?

You pad a batch to equal length. How does the model know to ignore the filler tokens?

Older tokenizers had an OOV problem. Why did byte-level BPE kill it?

Before the tokenizer even starts splitting, normalization runs. What does it do and why?

BPE learned 50,000 merge rules during training. What is a merge rule, and where does it live at inference?