MCP Explained: The Shared Plug That Connects AI Models to Tools

Business Pill 41 · The shared plug for AI tools

Every link between an AI model and a company system can be a custom build. The Model Context Protocol, MCP, replaces that with one shared plug.

A short explainer video. The numbers in it are round numbers for illustration.

The Short Answer

An engineer is teaching a robot to use the company systems. The calendar needs one custom connector. The customer database needs another. The invoices need a third.

Then two more robots arrive. With three robots and 10 systems, that is 30 connectors to build and to maintain.

One Shared Plug

So the industry agreed on one shared plug. It is called the Model Context Protocol, MCP for short: a standard way to connect an AI model to tools and data.

Now each system builds one plug, and each robot builds one socket. That is 13 pieces instead of 30.

A Worked Example

The arithmetic uses the video’s round numbers. Without a standard, every robot needs its own connector to every system: 3 robots times 10 systems is 30.

With the standard, each of the 10 systems builds one plug and each of the 3 robots builds one socket: 10 plus 3 is 13. This publication’s arithmetic from the video’s example: that is 17 fewer pieces.

In the video’s words, custom connectors multiply, while a shared plug adds up.

Why It Matters

A tool built once works with every assistant that speaks the standard. That is the business point: the work of connecting is done once, on the standard, not again for each assistant.

So the question to ask is whether the tools we buy speak the shared standard.

The Question to Ask

1. Do the tools we buy speak the shared standard?

See It in the News

Shopify Brings Agent Tools Into Checkout. A news piece on agent tools reaching a checkout flow through a standard connection.

More Business Pills

• The Memory Wall: Why a Faster AI Chip Is Not Faster AI
• Tokens per Watt: What an AI Data Centre Actually Produces
• Why AI Can’t Be Both Instant and Cheap: Latency vs Throughput
• The Model and the Harness: Why Same-Model Products Differ
• Context, Not Capability: Why a Smart AI Model Gives Poor Answers
• Discardable Software: When Code Is Cheap Enough to Throw Away
• Human in the Loop vs Human on the Loop: Supervising AI Agents
• The AI Audit Problem: When Making Work Is Cheaper Than Checking It
• AI Evaluation as Acceptance Test: How to Know It’s Good Enough
• Extensibility Is Control: Who Holds the Power in an AI Product
• RLHF Explained: How an AI Model Learns What People Prefer
• Pretraining Explained: How an AI Model Learns Before Anyone Teaches It
• Fine-Tuning Explained: How to Adapt a General AI Model to One Job
• Tokens Explained: The Unit AI Reads, Writes and Bills In
• Embeddings Explained: How a Machine Compares Meaning
• RAG Explained: How a Model Answers From Your Documents
• AI Hallucination Explained: Why Models State False Things
• Distillation Explained: How a Small Model Learns From a Large One
• Reasoning Models Explained: What Changes When AI Thinks First
• Tool Use Explained: How an AI Model Goes From Text to Action
• Capex and Depreciation Explained: Why Chip Lifetime Drives AI Profits
• Run-Rate Revenue Explained: What an AI Company’s Number Means
• Backlog Explained: Revenue That Is Signed but Not Yet Earned
• Switching Costs Explained: Why It Is Hard to Leave an AI Supplier
• Temperature Explained: The Dial That Sets How Predictable an AI Model Is
• Guardrails Explained: Rules Enforced Around an AI Model, Not Inside It
• Benchmarks Explained: Why a Test Score Is Not Your Own Result
• Agent Memory Explained: How an AI Assistant Remembers You Between Chats
• Quantization Explained: How a Large AI Model Is Shrunk to Fit
• Parameters Explained: Where an AI Model’s Knowledge Lives
• Scaling Laws Explained: Why AI Labs Keep Building Bigger
• Synthetic Data Explained: When a Model Writes Its Own Training Examples
• Transformers and Attention Explained: How AI Reads Every Word at Once

Business Engineer

The Map of AI

The Business Engineer framework maps where each part of the AI stack sits and who holds the leverage. These pills are short lessons from the same library.

Business Engineer

the Map of AI — 200+ companies across 9 layers

Read →

Business Engineer

the AI value chain — a multi-layered analysis

Read →

Explore the Map of AI →