Glossary · AI Agents

What is Model Context Protocol (MCP)?

An open standard for connecting AI applications to tools and data sources through reusable servers.

In more detail

A service exposes its tools once as an MCP server; any MCP-compatible assistant or agent can then discover and use them, instead of custom glue code for each app.

Example

A GitHub MCP server lets an assistant read issues and open pull requests.

Learn it properlyTool Calling Explained: How AI Agents Use Functions and APIs11 min lesson · AI Agents

Related terms

Full glossary

EmbeddingA list of numbers that represents the meaning of a piece of text, so similar meanings are close together.Human-in-the-LoopA design where a person reviews or approves an AI system’s action before it takes effect.ReAct PatternAn agent pattern that alternates reasoning about the next step with acting through a tool, then observing the result.Tool Calling (Function Calling)A model capability where the AI returns a structured request to run a function with specific arguments, instead of plain text.Vector DatabaseA database designed to store embeddings and quickly find the most similar ones to a query.