---
id: "prereq-mcp-d24"
type: "prereq"
source_timestamps: ["00:06:05", "00:12:13"]
tags: ["technical-knowledge"]
related: ["entity-mcp", "entity-anthropic", "concept-unified-context-infrastructure", "action-build-mcp-infrastructure"]
reason: "Necessary to grasp the proposed architectural solutions for Layer 1 of the Intent Gap."
sources: ["s24-prompt-engineering-dead"]
sourceVaultSlug: "s24-prompt-engineering-dead"
originDay: 24
---
# Familiarity with Model Context Protocol (MCP)

## What Is Required

The speaker references **MCP (Model Context Protocol)** as the emerging standard for context infrastructure without fully explaining its technical mechanics. Listeners are expected to know:

- It was developed by [[entity-anthropic-d24]].
- It is positioned as an open, vendor-agnostic standard.
- It targets the problem of connecting AI models to organizational data sources without lock-in.
- Per the speaker, it was donated to the Linux Foundation in December 2025.

Full entity profile: [[entity-mcp]].

## Why This Matters for the Argument

MCP is the **canonical implementation** the speaker proposes for Layer 1 of the [[framework-intent-gap-layers]] — [[concept-unified-context-infrastructure]]. Without familiarity, the proposed solution to [[concept-shadow-agents]] is opaque.

The corresponding action item is [[action-build-mcp-infrastructure]].

## Enrichment Caveat

The enrichment overlay was **unable to verify** MCP as described — no canonical URL or Linux Foundation donation was matched. Listeners should treat MCP as either an emerging-but-not-yet-canonical standard or a speaker-projected protocol. The directional architectural move (vendor-agnostic context layer with central governance) is sound regardless of the specific protocol's status.