Home Glossary
HomeGlossaryAI Agent
MCP Glossary

AI Agent

TL;DR

An AI agent is an autonomous software system powered by an LLM that can plan, take actions via tools, observe results, and iterate toward a goal. Unlike a chatbot that just replies, an agent does things: it calls APIs, edits files, spawns sub-tasks, and makes decisions without step-by-step human guidance.

In depth

An AI agent wraps an LLM in a loop: perceive → plan → act → observe → repeat. The LLM is the reasoning engine; tools are its limbs; memory (short-term context + long-term stores) is its continuity. The agent's autonomy comes from its ability to choose which tool to call next based on the goal and what it has learned so far.

Agents range from simple (single-step tool use) to complex (multi-agent orchestration with sub-agents, playbooks, and self-reflection). Claude Code, Cursor, and Windsurf are agentic coding tools — they plan a change, edit files, run tests, and iterate on failures autonomously.

Modern agents use MCP as their tool protocol. The LLM sees a list of MCP tools (from connected servers), picks one, calls it, reads the result, and decides the next step. This decouples the reasoning (LLM) from the capabilities (MCP servers).

Agents are characterized by three properties: **autonomy** (decide next action), **tool use** (call external capabilities), and **memory** (remember context across turns). Add multi-agent orchestration and you have the current frontier.

Examples

  • 1
    Claude Code editing your codebase autonomously to implement a feature
  • 2
    An internal 'SRE agent' that triages alerts and restarts services
  • 3
    A research agent that browses, summarizes, and writes a report
  • 4
    A customer-support agent that reads tickets, categorizes, and drafts replies
  • 5
    A trading agent that watches market feeds and executes strategies

What it's NOT

  • ✗An AI agent is NOT just a chatbot — it takes autonomous actions, not just replies.
  • ✗An AI agent is NOT always multi-step — simple agents can do one tool call and return.
  • ✗An AI agent does NOT have to use MCP — but MCP is becoming the standard tool protocol.
  • ✗An AI agent is NOT necessarily AGI — current agents have narrow autonomy within bounded tasks.

Related terms

Tool UseFunction CallingAgentic WorkflowLarge Language Model (LLM)Model Context Protocol (MCP)

See also

  • Anthropic on Agents

Frequently asked questions

What's the difference between an agent and a chatbot?

A chatbot replies. An agent acts. Agents call tools, modify state, and iterate — a chatbot is constrained to conversation.

Do agents need memory?

Yes, at least short-term (the conversation). Production agents also use long-term stores (vector DBs, JSON state) for persistence.

Can multiple agents work together?

Yes — multi-agent orchestration lets a 'manager' agent delegate sub-tasks to specialized 'worker' agents. Nanobot Enterprise and CrewAI use this pattern.

Build with MCP

Browse 300+ MCP servers, explore recipes, or continue learning the MCP vocabulary.

Browse MarketplaceAll terms