GLOSSARY

What is agent tooling?

Agent tooling is the set of callable tools a software product exposes so AI agents can operate it: the functions, schemas, and permissions that turn a product into something an agent can drive. For marketing teams, agent tooling determines whether a platform can be run by Claude or ChatGPT — or only by hand, in the vendor's UI.

From developer concept to buying criterion

"Tools" started as a developer concept: the functions an LLM is allowed to call, described by schemas, invoked during a conversation or task. The Model Context Protocol (MCP) standardized how products expose those tools, so any MCP-capable agent — Claude, IDE agents, custom harnesses — can connect to any MCP server without bespoke integration.

That standardization quietly turned agent tooling into a procurement question. If your team works alongside agents, a platform with no tool surface is a platform your agents can't touch — every workflow dead-ends at a human clicking through a UI. The tool count on a pricing page now matters the way "has an API" mattered in 2015.

What good agent tooling looks like

Four properties separate a real tool surface from a demo. Coverage: the tools span the product's actual operations, not a marketing subset — if a human can do it in the app, an agent can do it through a tool. Composability: tools are granular enough to chain (read segment → draft variant → stage placement → check lift), so the agent can build workflows the vendor never anticipated. Governance: scoped tokens, role gates, and human-review checkpoints, because "agent can act" must not mean "agent acts everywhere, unsupervised." Verifiability: every write has a read the agent can use to confirm what actually happened.

Agent tooling in AXO

AXO exposes 130+ MCP tools covering the full personalization loop: analytics and lift reads, campaign briefs, segment queries, variant drafting, placement changes, trigger management, and profile operations. The server runs as a hosted HTTP endpoint (no local install) or as a package, authenticated with scoped MCP tokens issued from the dashboard. The same operations are available over REST. Your team drives the app; your agents drive the tools; you decide where each is allowed to act without asking.

QUESTIONS PEOPLE ASK

What is MCP (Model Context Protocol)?

MCP is an open protocol, introduced by Anthropic in 2024, that standardizes how applications expose tools and context to AI models. A product ships an MCP server describing its tools; any MCP-capable client — Claude, IDE agents, custom harnesses — can then connect and operate the product without a bespoke integration.

How do marketing teams actually use agent tooling?

By delegating the operating work. Connected over MCP, an agent can audit which segments are underperforming, draft variants for review, stage them into placements, and report holdout lift — the same actions a person takes in the app, executed programmatically and at a breadth no team could click through. Humans keep the review gates and the policy decisions.

Which personalization platforms expose MCP tools?

As of mid-2026, only a handful of experimentation and personalization vendors ship MCP servers, and coverage varies from a few read-only tools to full operational surfaces. AXO exposes 130+ MCP tools spanning analytics, segments, variants, placements, triggers, and profiles. When evaluating any platform, ask for the tool list — the delta between "has an MCP server" and "agent can run the product" is large.

KEEP GOING
AXO's MCP server: 130+ toolsWhat is agentic software?Developer & API docs
See the agentic experience layer on your own traffic.
One tag, live in about 15 minutes.
Start free trial →
MORE FROM THE GLOSSARY