Skip to main content

What can my agents do?

Every server, tool, hook and skill. Cross-server attack paths with evidence. Yes/no answers computed from the graph. aspex scan · aspex explain

What did they actually do?

Tool calls from your clients’ own logs. Kill chains and provenance labeled OBSERVED, INFERRED, POSSIBLE. aspex trace · aspex explore

What changed?

New tools, poisoned descriptions, wider scope, new attack paths. Exit 1 in CI on drift you did not accept. aspex lock · verify · diff

​
Run this first

aspex with no arguments joins your MCP configs with your clients’ logs and shows one screen. Real output from the maintainer’s machine, nothing sent anywhere:
Then a menu opens underneath. The front door →

​
How it reasons

Three ideas are kept apart on purpose. Everything Aspex prints is one of them, and says which.

​
What Aspex is not

  • Not a proxy. Never in your agent’s request path.
  • Not a blocker. It shows you. You decide.
  • Not a SaaS. No account, no telemetry. The only network call is the download.
  • Not omniscient. Cloud connectors it cannot scan are shown as “in use, never scanned”.

Quickstart

Install, see what your agents can do, harden it. About a minute.

Common workflows

Task first, command second. Where to start for what you want to do.

How Aspex reasons

Why a finding exists, and how to reproduce it.

Using a coding agent?

These docs are available as llms.txt for your agent to read.