The agents chain what they find: orphaned subdomain, unauthenticated API, cloud key, production. If the path completes, you see it drawn out, with the proof.
Every validated finding goes out with its evidence to Slack, Jira, PagerDuty or your assistant over MCP. Tap a destination to see how it arrives.
Personal data exposed in an unauthenticated API
api.yourcompany.com/v1/users · CVE-2026-109618
Critical: personal data exposed at api.yourcompany.com/v1/users. Reproduced by the agent, evidence in the thread.
Personal data exposed in an unauthenticated API · priority Highest · assigned to the API team.
Incident opened for the on-call owner with the finding, the host and the severity.
"Which critical findings do I have open?" · The assistant you already use queries Merabytes over MCP and answers with the real state.
We give them your perimeter, real offensive tools and one goal: find what an attacker would find first.
They discover exposed hosts, APIs and services. The same thing an attacker would do in their first hour, without touching anything in production.
Claude Sonnet, GLM or DeepSeek Flash: each task goes to the agent that solves it best. No lock-in to a single provider.
Every vulnerability arrives with its CVE, the evidence and the steps to close it. To Jira, Slack or your EDR. No middleware.
A second agent tries to reproduce every finding with a different model. If it can't, we don't report it as critical. That way the list you get is short and real.
When an agent tests your perimeter, responses can carry real emails, national IDs, phone numbers or bank accounts. A filter sits between the tool and the model and redacts every response before the agent reads it. The LLM works with placeholders, and your company's and your customers' data never reaches the model provider. It is designed to respect the GDPR and the confidentiality of your data.
The agents talk directly to what you already have: EDR, SIEM, ticketing, identity and cloud. No glue in between.
yourcompany.com is our test environment. The numbers come straight from the agents.
÷14 in 13 weeks
From 14 open critical findings to 1. Lab environment data, full weeks.
| Week | Critical | Exposed |
|---|---|---|
| Aug 5 | 14 | 38 |
| Aug 12 | 13 | 36 |
| Aug 19 | 11 | 33 |
| Aug 26 | 11 | 30 |
| Sep 2 | 9 | 27 |
| Sep 9 | 8 | 25 |
| Sep 16 | 6 | 21 |
| Sep 23 | 5 | 18 |
| Sep 30 | 4 | 15 |
| Oct 7 | 3 | 12 |
| Oct 14 | 2 | 9 |
| Oct 21 | 1 | 7 |
| Oct 28 | 1 | 5 |