Skip to content

Glossary

What is the Model Context Protocol?

The Model Context Protocol, or MCP, is an open standard for connecting AI assistants to external tools and data in a consistent way.

  • Also called MCP

What it means

MCP defines how an AI application discovers and uses tools offered by other systems. Anthropic introduced it in November 2024, OpenAI and Google DeepMind adopted it in 2025, and in December 2025 it was donated to the Agentic AI Foundation under the Linux Foundation.

The protocol has continued to evolve. The specification dated July 28, 2026 made the core of the protocol stateless, which simplifies hosted servers.

Why it matters for a business

Before MCP, each AI connection was built separately for each app. With a common standard, a connection built once works across many assistants, so investments in connecting your systems are not tied to one AI provider.

A business example

Things to watch

  • Treat each server like a new user with access to your systems.

  • Check the specification version your tools support.

  • Keep sensitive actions behind approval.

  • Review servers when their maintainers publish updates.

Keep exploring

FAQ

Questions about model Context Protocol

Have a question that is not here? Ask us directly.

Start a project

Tell us what you want to build. We will show you a faster path.

Send a short brief. We reply with questions, a suggested plan and an estimate you can compare with other offers.

Your privacy choices

We use necessary storage to run this site. With your permission we also use Google Analytics to see which pages help people, and load maps from Google. You can change this at any time. Read the cookie policy.