AI Support & Agents

Model Context Protocol (MCP)

Definition

The Model Context Protocol (MCP) is an open standard that defines a common way for AI applications to connect to external tools, data sources, and systems — so a model can access them through a single, consistent interface instead of a custom integration for each.

Also known as: MCPMCP protocol

How it works

MCP standardizes the connection between an AI client (the app running the model) and MCP servers, which expose tools, resources, and data. Rather than building a bespoke integration for every system, developers connect any MCP-compatible server to any MCP-compatible client, and the model can discover and call what's available through the shared protocol.

It's often described as a universal connector for AI — a common language that lets models plug into files, databases, APIs, and business systems without one-off glue code for each one.

Why it matters for support

For AI in support, MCP reduces the integration cost of giving an agent access to the systems it needs — CRMs, order databases, internal tools. A shared standard means new capabilities can be added faster and with less maintenance than hand-built connectors.

Frequently asked

What does MCP do?

It provides a standard interface for connecting AI models to external tools and data, so one integration approach works across many systems instead of a custom build for each.

How is MCP related to tool use?

Tool use is a model calling an external function; MCP is a standardized way to expose and connect those tools so the same model can reach many systems consistently.

Integrations directory

Related terms

Tool Use

Tool use is the ability of an AI model to invoke external functions, APIs, or systems — like looking up an order or issuing a refund — instead of only generating text, so it can act on real data rather than just describe it..

Function Calling

Function calling is a capability that lets a language model request that a predefined function or API be run — returning the function name and structured arguments — so the model can fetch live data or take actions instead of only generating text..

Custom Tools

In Macha, a custom tool lets an AI agent call any HTTP API endpoint you configure — so an agent can read live data or take an action in a system Macha doesn't have a built-in connector for, without waiting for a marketplace app..

Connectors

Connectors are Macha's built-in integrations.

Agentic AI

Agentic AI is AI that doesn't just answer questions but takes actions — it plans multi-step tasks, calls tools and APIs, and works toward a goal end to end with little or no human intervention..

Put these ideas to work

Macha is an AI agent layer that sits on top of the help desk you already run — Zendesk, Freshdesk, Front, Intercom, or Gorgias.

Start Trial