AI & MCP Glossary

Clear, concise definitions of key terms in AI development, Model Context Protocol, and knowledge management. Updated for 2026.

A

AI Memory

AI memory refers to mechanisms that give AI assistants persistent knowledge across sessions. Unlike the ephemeral context window that resets with each conversation, AI memory stores learned patterns, preferences, and facts that persist between interactions, enabling AI systems to improve and personalize over time.

K

Knowledge Base

In the context of AI development, a knowledge base is a structured collection of documents, patterns, and rules that AI agents can search and reference during their work. Unlike general training data, a knowledge base contains curated, project-specific information — architecture decisions, coding patterns, API documentation — that keeps AI responses accurate and consistent with your codebase.

M

MCP Server

An MCP server is a program that exposes tools, resources, and prompts to AI assistants through the Model Context Protocol. MCP servers act as bridges between AI models and external systems — databases, APIs, file systems, or knowledge bases — allowing AI to interact with them through a standardized interface.

Model Context Protocol (MCP)

Model Context Protocol (MCP) is an open standard created by Anthropic that enables AI assistants to connect with external data sources and tools through a unified interface. It provides a standardized way for AI models to access context, execute tools, and interact with services without custom integrations for each provider.

R

RAG (Retrieval-Augmented Generation)

Retrieval-Augmented Generation (RAG) is a technique that enhances AI responses by retrieving relevant information from an external knowledge base before generating an answer. Instead of relying solely on training data, RAG systems search a curated dataset, inject the most relevant documents into the prompt context, and generate responses grounded in factual, up-to-date information.

S

Semantic Search

Semantic search is an information retrieval technique that understands the meaning and intent behind a query, rather than matching exact keywords. It uses vector embeddings to find content that is conceptually related to the search query, even when different words are used. This enables searching by meaning — 'how to test APIs' would match content about 'endpoint validation strategies.'

V

Vector Embeddings

Vector embeddings are numerical representations of text (or other data) in a high-dimensional space where semantically similar content is positioned close together. They enable AI systems to perform semantic search — finding content by meaning rather than exact keyword matches — by converting text into fixed-length arrays of numbers that capture semantic relationships.