---
id: "prereq-mcp"
type: "prereq"
source_timestamps: ["§ Can Someone Please Define a \"Harness\"?", "§ Memory & Search for Continual Learning"]
tags: ["protocols", "tool-use"]
related: ["entity-context7", "concept-progressive-disclosure"]
reason: "Necessary for understanding modern tool integration and progressive disclosure techniques."
canonicalUrl: "https://www.anthropic.com/news/model-context-protocol"
---
# Model Context Protocol (MCP)

## What It Is

The **Model Context Protocol (MCP)** is a standard introduced by Anthropic for connecting AI models to external data sources and tools. It defines how an LLM (or agent harness) discovers and invokes external capabilities — *“MCP servers”* expose tools, prompts, and resources; *“MCP clients”* (typically the harness) consume them.

## Why It Matters for This Source

The article references "MCPs" and "MCP tools like [[entity-context7|Context7]]" without defining the acronym. It assumes familiarity with MCP as the standard for tool integration.

[[concept-progressive-disclosure]] is specifically motivated by MCP: loading too many MCP servers' tool descriptions at agent start causes early [[concept-context-rot|context rot]]. Progressive disclosure manages this by injecting only the relevant subset on demand.

## Canonical URL

https://www.anthropic.com/news/model-context-protocol