Skip to main content
The agent connector lets your own AI coding agents read your Amnify security data and act on it, inside the same permission boundary as the product. It speaks the Model Context Protocol, so any client that supports MCP can connect.

​
Connecting

1

Point your agent at Amnify

Add Amnify as a connector in your AI coding agent, using the endpoint below.
2

Sign in and choose the organization

You authenticate as yourself and pick the organization the connection is for.
3

Approve the access

The consent screen names the client, the organization, and what is being requested, in plain language.

​
What a token can reach

A token is bound to exactly one organization at the moment it is issued. It cannot be switched to another one later, and connecting a second organization requires a separate authorization. Everything a client can reach is filtered by that organization, using the same isolation rules as the web application. See Data security.

​
What it is useful for

Ask in context

Query findings, scans and context from wherever you already work, without switching tools.

Bring security into your own agents

Let a coding agent check the security state of a service before it changes it.

Trigger work

Start a scan or pull the current state of a scope as part of your own automation.

Report

Pull the current picture into your own reporting rather than exporting by hand.

​
Revoking

Revoke an agent’s access at any time from your organization settings. Access ends immediately.