# Model Context Protocol

> An open standard for plugging tools and data into AI assistants the same way every time.

- Level: Intermediate
- Topics: AI, Software
- URL: https://tidbit.legios.com.ar/model-context-protocol/
- In Spanish: [Model Context Protocol](https://tidbit.legios.com.ar/es/model-context-protocol/)

The **Model Context Protocol** (MCP) is an open standard that defines how an AI application talks to outside tools and data. Anthropic published it in November 2024, and it was soon adopted across the industry, including by OpenAI, Google and Microsoft. Before MCP, every AI app needed its own custom integration for every service it wanted to use; with MCP, a tool built once works with any app that speaks the protocol.

It has two sides. An **MCP server** is a small program that wraps some system (your files, a calendar, a company database, GitHub, a design tool) and describes what it offers: **tools** the AI can call to do things, **resources** it can read, and ready-made **prompts**. An **MCP client** lives inside the AI app, such as Claude, ChatGPT or a code editor, connects to servers, and shows the model what is available. When you ask 'what is on my calendar tomorrow?', the model decides to call the calendar server's tool, gets the answer, and uses it in its reply. Servers can run on your own computer or remotely over the internet.

That makes MCP a building block for AI agents, which need to act, not just talk. It also deserves care. A server can do whatever its permissions allow, so a careless or malicious one could read private data or take actions you did not intend, and text coming back from a tool can carry hidden instructions meant to trick the model (prompt injection). Install servers only from sources you trust, give them the minimum access they need, and keep an eye on what an assistant asks to do.

## An analogy

Like the standard electrical outlet: appliance makers do not need a deal with each house, they just use the standard plug. MCP is that outlet for AI apps, and each MCP server is an appliance you can plug in.

## Keep in mind

- An open standard released by Anthropic in November 2024.
- Servers expose tools, data and prompts; clients sit inside AI apps.
- Build an integration once and it works with many AI apps.
- A server acts with your permissions, so install only trusted ones.

## Go deeper

- [What is the Model Context Protocol? (official site)](https://modelcontextprotocol.io/docs/getting-started/intro)
- [Introducing the Model Context Protocol (Anthropic)](https://www.anthropic.com/news/model-context-protocol)
- [Model Context Protocol on Wikipedia](https://en.wikipedia.org/wiki/Model_Context_Protocol)

## Related terms

- [Open standard](https://tidbit.legios.com.ar/open-standard/): A public rulebook anyone can follow, so products from different makers work together.
- [Artificial intelligence](https://tidbit.legios.com.ar/artificial-intelligence/): Getting computers to do things that, until recently, only people could do.
- [Anthropic](https://tidbit.legios.com.ar/anthropic/): The AI company behind Claude, built around making models safe and useful.
- [OpenAI](https://tidbit.legios.com.ar/openai/): The company that made ChatGPT and turned AI into a household topic.
- [Google](https://tidbit.legios.com.ar/google/): The search company that gives most products away and makes its money on ads.
- [Microsoft](https://tidbit.legios.com.ar/microsoft/): The company of Windows and Office, now just as much a cloud company with Azure.
- [Database](https://tidbit.legios.com.ar/database/): An organized store of data that programs can search and update safely.
- [GitHub](https://tidbit.legios.com.ar/github/): A website where teams store their code with Git and work on it together.