Agents & tools
MCP (Model Context Protocol)
Definition
MCP is an open standard for connecting AI models to external tools and data sources. It replaces bespoke per-integration code with one protocol any compatible client can use.
Before MCP, every AI application implemented its own integration layer, and every tool had to be rebuilt for each client. MCP defines a common protocol so an MCP server exposing, say, your database works with any MCP-capable client.
An MCP server exposes three primitive types: tools (actions the model can invoke), resources (data it can read), and prompts (reusable templates). Clients discover what a server offers at runtime.
The practical effect is a growing ecosystem of reusable connectors. It is also why "write an MCP server" has become a common way to make an internal system available to AI assistants without building a bespoke integration for each.
Related terms
AI agent
An AI agent is a system where a model plans and takes actions through tools in a loop, rather than producing a single response. It decides what to do next, does it, observes the result, and continues until the goal is met.
Function calling
Function calling lets a model request that your code run a specific function with specific arguments. You expose tool definitions; the model returns a structured call, your code executes it, and the result goes back into the conversation.
Tool use
Tool use is a model invoking external capabilities — search, code execution, database queries, APIs — to do things it cannot do from parameters alone, such as fetching current data or performing exact arithmetic.
ReAct pattern
ReAct (Reason + Act) is the core agent loop: the model reasons about what to do, takes an action via a tool, observes the result, then reasons again. It repeats until it can answer.
Guardrails
Guardrails are the constraints that keep an AI system inside acceptable behaviour — input validation, output filtering, topic restrictions, action limits and human approval gates.
Human in the loop
Human in the loop means inserting a person at decision points in an automated workflow — typically to approve consequential actions or review low-confidence outputs before they take effect.
Put this into practice
Understanding the term is step one. Our free courses and tools let you actually use it.