GLOSSARY

What is MCP (Model Context Protocol)?

The Model Context Protocol (MCP) is an open standard, introduced by Anthropic in 2024, for connecting AI models to software. A product ships an MCP server that describes its operations as callable tools; any MCP-capable agent can then connect and operate the product. MCP is to AI agents what the API was to integrations.

How it works, minus the jargon

An MCP server is the product's side of the plug: a list of tools, each with a name, a description, and a typed schema for its inputs. An MCP client is the agent's side — Claude, an IDE agent, a custom harness. When they connect, the agent reads the tool list and can call any of them: fetch a report, create a segment, draft a variant. Authentication is typically a scoped token, so the agent holds exactly the permissions it was granted and nothing else.

The point of the standard is that neither side needs to know about the other in advance. Any MCP-capable agent can drive any MCP server, the way any browser can load any website.

Why marketers should care

MCP quietly turned "can my agent drive it?" into a procurement question. If your team works alongside agents, a platform with no MCP surface is a platform your agents can't touch — every automated workflow dead-ends at a human clicking through a UI. Tool coverage now matters the way "has an API" mattered a decade ago, and the delta between "has an MCP server" and "an agent can genuinely run the product" is large. Ask for the tool list.

AXO's MCP server exposes 130+ tools spanning the full personalization loop — site crawling, segments, variants, placements, triggers, lead capture, pipeline, and holdout measurement — hosted, with scoped tokens, and mirrored over REST.

QUESTIONS PEOPLE ASK

Is MCP only for developers?

No. Connecting an MCP server to an agent like Claude is closer to installing an integration than writing code: point the client at the server's endpoint, authenticate with a token, and the agent can use the tools. Developers build MCP servers; marketers increasingly just use them.

What is the difference between MCP and an API?

An API is designed for programmers to integrate against — each integration is bespoke code. MCP is designed for AI agents: tools are self-describing, with names, descriptions, and schemas a model can read and act on directly, so any MCP-capable agent can operate any MCP server without custom integration work. Most products that ship MCP servers expose the same operations over both.

Which marketing platforms support MCP?

As of mid-2026, a small but growing set — and coverage varies enormously, from a few read-only reporting tools to full operational surfaces. AXO exposes 130+ MCP tools covering the entire product. When evaluating a vendor's MCP claim, ask for the tool list and check whether an agent can complete a real workflow end to end, or only fetch reports.

KEEP GOING
What is agent tooling?We gave the agent 130+ toolsAXO's MCP server
See the agentic experience layer on your own traffic.
One tag, live in about 15 minutes.
Start free trial →
MORE FROM THE GLOSSARY