The words of agent security, defined plainly

What an AI agent can get to, directly or through other identities, tokens and tools.

Reach is about authority, not activity: an agent can reach data it has never touched.

A chain of identities, grants and tools that leads from one starting point to sensitive data.

A path is a route that exists, not proof that anyone used it.

The single grant, key or connection whose removal cuts the most paths.

Fixing a breakpoint closes many routes with one change.

The data stores whose exposure would hurt the company most, such as customer records or production databases.

Paths are ranked by how close they get to this data.

How many hops separate an agent from a production system.

A short distance means little stands between a mistake and real damage.

A service that gives AI agents tools and data through the Model Context Protocol, usually with credentials behind it.

Every connected MCP server is a place where authority enters.

An account that acts without a person: service accounts, API keys, bots, OAuth apps and agents.

They outnumber people in most companies and are often owned by no one.

Permission a user or admin gives an app, often an AI tool, to act in another service.

Grants stay valid until someone revokes them.

A shared identity used by software, which agents often reuse.

Reuse lets one agent inherit all of an account's access.

An AI agent that runs in your environment without an owner or approval on record.

You cannot review the reach of an agent you do not know about.