---
id: "prereq-mcp-understanding-d48"
type: "prereq"
source_timestamps: ["00:02:29"]
tags: ["protocols", "agents"]
related: ["concept-mcp", "action-mcp-growth-hack"]
reason: "Required to understand how tools like Remotion and Blender are being controlled by Claude via the command line."
sources: ["s48-markdown-design-meeting"]
sourceVaultSlug: "s48-markdown-design-meeting"
originDay: 48
---
# Understanding of Model Context Protocol (MCP)

## Prerequisite

A working understanding of the [[concept-mcp-d48|Model Context Protocol (MCP)]] and how LLMs interact with local environments and external APIs.

## Why It's Required

The video assumes the audience already understands the basic mechanics of how an LLM (e.g. [[entity-claude-d48|Claude]]) discovers tools, reads their schemas, and executes calls against them. Without this background, key claims dissolve into hand-waving:

- How is [[entity-remotion|Remotion]] 'controlled by Claude'? — Via MCP.
- How does [[entity-blender-mcp|Blender MCP]] 'expose' a Python API? — As an MCP server.
- Why is [[action-mcp-growth-hack|making your product an MCP server]] a growth hack? — Because agents call MCP servers natively.

## What 'Understanding MCP' Means Practically

- LLMs are not magic — they call tools through structured protocols.
- An **MCP server** advertises capabilities (tools / resources / prompts).
- An **MCP client** (the agent) reads those capabilities and invokes them.
- All of this runs locally or networked, and is invocable from a terminal.

## If Your Audience Lacks This

Ground them in:
1. The general LLM-tool-use loop (system prompt → tool schemas → invocation → response).
2. Why a *protocol* matters (interoperability vs. bespoke integration).
3. The MCP-specific flavor (server/client roles, transport).

## Related
[[concept-mcp-d48]] · [[claim-mcp-usb-for-ai]] · [[action-mcp-growth-hack]] · [[entity-claude-d48]]