Skip to content
LinkedInX

What is MCP?

About 5 minutes

Target audience: Those curious about how AI agents connect to external tools, those who've heard of MCP but want a clear explanation
Prerequisites: What Is an AI Agent?

The Model Context Protocol (MCP) is an open standard for connecting AI applications to external tools, resources, and environments. The official MCP documentation describes it as a USB-C-like standard connection for AI applications.[1]

Imagine someone who only speaks English trying to have a conversation with people who speak French, German, and Spanish. Direct communication is impossible because they speak different languages. What they need is an interpreter.

AI models face a similar situation. Large Language Models (LLMs) can only answer based on the knowledge contained in their training data. They cannot directly access external information or tools such as real-time weather, breaking news, or corporate databases.

MCP plays the role of that interpreter. It stands between AI agents and various external tools and resources, enabling bidirectional communication through a common language — the protocol.

I think of MCP as USB-C for AI systems.

Before USB-C, connecting devices required different cables and standards for each piece of hardware. With the widespread adoption of USB-C as a common standard, a single cable can now connect smartphones, laptops, displays, and many other devices.

MCP provides the same kind of universal standard. AI applications connect to diverse external tools — databases, file systems, web APIs, code execution environments — through a single “port” called MCP.

LLMs excel at generating text, but they have the following limitations:

LimitationDescription
Knowledge cutoffNo awareness of events that occurred after training completed
Real-time informationCannot access current weather, stock prices, or news
External system integrationCannot directly operate databases or APIs
State persistenceCannot make permanent changes such as writing to files

MCP supplements these limitations, enabling AI agents to work with real-world tools and information.

MCP consists of three components. Each is explained in detail on its own page.

ComponentRoleDetails
HostUser-facing AI applicationArchitecture
ClientComponent handling communication with MCP serversArchitecture
ServerExternal program that provides tools and resourcesArchitecture

MCP servers can also provide three main types of capabilities. Tools, Resources, and Prompts are defined in the official documentation.[2][3][4]

CapabilityOverviewDetails
ToolsFunctions an AI can invoke (with effects/side effects)Capabilities
ResourcesRead-only data provisionCapabilities
PromptsPredefined prompt templatesCapabilities
  • MCP is a standardized protocol connecting AI models to external tools and resources
  • Like an interpreter or USB-C, it provides a common connection standard between different systems
  • It solves the challenges of LLM knowledge limitations, real-time information access, and external system integration

Q: Which company developed MCP?

A: Anthropic published MCP as an open standard, and the current concepts and specifications are organized in the official Model Context Protocol documentation.[1]

Q: What do I need to use MCP?

A: I need an AI application that implements an MCP client and an MCP server. The MCP architecture describes a Host containing MCP Clients that connect to MCP Servers.[5]

Q: How is MCP different from an API (Application Programming Interface)?

A: An API defines a connection interface to a specific service. MCP is a meta-protocol that standardizes communication between AI models and tools — MCP servers often call APIs internally. MCP does not replace APIs; rather, it makes it easier for AI to use APIs.

  1. Model Context Protocol, What is the Model Context Protocol?
  2. Model Context Protocol, Tools
  3. Model Context Protocol, Resources
  4. Model Context Protocol, Prompts
  5. Model Context Protocol, Architecture overview