Glossary

Model Context Protocol (MCP)

An open standard that lets AI agents connect to tools, data sources, and actions through a common interface.

The Model Context Protocol (MCP) is an open standard for connecting AI models and agents to external tools, data, and actions. Instead of every application inventing its own integration, MCP defines a common client–server interface: an MCP server exposes capabilities (read a file, query a database, run a workspace action), and any MCP-capable agent can use them.

For developers, MCP is what turns a chat-only model into an agent that can take real actions. A terminal like Agents UI ships MCP tools for sessions, projects, files, and SSH, so agents can execute concrete workspace operations rather than only suggesting commands.

Learn more

Related guides on the Agents UI blog and related terms in this glossary.

Try Agents UI

A native terminal for AI coding agents with persistent sessions, SSH workflows, and built-in editing.

Download View on GitHub

Related

MCP Server

A program that exposes tools and data to AI agents over the Model Context Protocol.

AI Coding Agent

An AI program that autonomously reads, writes, and runs code to complete development tasks.

Agentic Coding

A workflow where an autonomous AI agent plans and executes multi-step coding tasks, not just single completions.

Model Context Protocol For Developers Practical Guide

Read the guide →

Best Mcp Servers For Developers 2026

Read the guide →