What is the Model Context Protocol (MCP)?
LLM & AILevel: IntermediateTool Use & MCP
What is the Model Context Protocol (MCP)?
Hints
- Identify the stage: pretraining, adaptation, generation or evaluation.
- Name the inputs, constraints and a case where the approach fails.
Answer
MCP (Anthropic, 2024) is an open standard that defines how AI applications connect to tools and data sources — "HTTP for AI tool use":
[MCP Host: Claude/Cursor/VS Code]
↕ MCP Protocol
[MCP Server: GitHub, Slack, Database, File System...]
Three primitives:
- Tools — functions the model can call (like function calling)
- Resources — data sources the model can read (files, database records)
- Prompts — reusable prompt templates the host can invoke
Why it matters: before MCP, every AI app wrote custom integrations for every tool. With MCP, any MCP-compatible model can use any MCP-compatible server without custom glue code. Growing ecosystem of community MCP servers.
Source and licence: JustInCache & contributors — Awesome AI Interviews · Apache-2.0