Home / Solutions / Vortex MCP
Vortex MCP

Pentest your app before you commit.

Pre-commit AI pentesting in your editor. Vortex MCP runs a real dynamic pentest against your locally-running app — from Claude Code or any MCP client — and hands back exploit-checked findings with remediation guidance.

The same Vortex engine as the platform — delivered at dev-time. Your app traffic originates on your machine.

Claude Code — vortex-mcp SQLi found
you ›pentest my app on localhost:3000
vortex ›Starting local executor (Docker) — blackbox profile…
vortex ›crawl complete — 34 endpoints discovered
vortex ›error-based SQL injection confirmed on ?q=
vortex ›1 critical, 2 medium — remediation guidance ready
Claude Code start_pentest SQLi found SARIF 2.1.0

The Problem

AI writes code faster than anyone can review it for real bugs.

01

Code ships at machine speed.

AI generates whole features in seconds. The volume outpaces human review, and insecure patterns land in the branch before anyone reads them.

02

Linters pattern-match. Attackers don't.

SAST and linters flag shapes in source. They miss auth bypasses, injection, and logic flaws that only exist when the app is actually running.

03

Real pentests arrive too late.

A proper dynamic test happens after merge — sometimes once a year. The exploitable bug was reachable the whole time, in every commit since.

How It Works

A cloud brain. A local executor. Your app never leaves your machine.

You ask Claude to pentest your app. The Vortex brain in the cloud plans the attack and streams tool commands down to a local executor running in a Docker container on your machine — which runs the tools against your locally-running app.

Request path

You + Claude Ask in your editor "pentest localhost:3000"
Cloud Vortex brain plans & streams tool commands
Your machine Local executor Docker container, runs the tools
Target Your running app localhost:3000

Under the hood: industry-standard dynamic security tools, orchestrated by the Vortex brain — real DAST, not pattern-matching.

Findings + remediation guidance return to your editor — exploit-checked, ready to fix before you commit.

Your source stays yours. App traffic originates on your machine. In blackbox mode the brain never sees your source code; greybox sends only derived context — routes, OpenAPI, stack — never source.

Capabilities

Real dynamic pentesting, at development time.

Real DAST, not static analysis

Live attack payloads against your running app — the flaws a code scanner can't see because it never runs the code.

The same Vortex engine

The pentest engine that powers the platform — delivered at dev-time, so what you fix locally matches what runs in CI and prod.

Runs from any MCP client

Claude Code, Cursor, Cline, Zed — or wired into CI. Any Model Context Protocol client can drive it.

Blackbox & greybox

Test blind like an outside attacker, or hand over derived context — routes, OpenAPI, stack — for deeper coverage. Never your source.

SARIF 2.1.0 output

Standards-compliant findings drop straight into code scanning dashboards and PR annotations — no glue code.

CI gate + scan modes

Fail the build on a severity threshold. Choose smoke, standard, or deep to trade speed for depth.

Security Posture

A local client that can't leak your crown jewels.

Vortex MCP is built so the powerful, proprietary parts stay server-side and the thing on your laptop is deliberately small and contained.

Brain-free client

The crown-jewel AI stays server-side. The local executor only runs tool commands it's told to run — there's no model or attack logic to extract from your machine.

Isolated container

Runs in an isolated container on your machine. The executor is a small, contained process that runs the tool commands it's given — kept separate from the rest of your environment.

Scoped auth

Authenticate with a scoped org API token or OAuth 2.0 device flow — approve a code in your browser, no long-lived secret pasted into config.

Only what you own

An "only test what you own" guardrail keeps scans pointed at targets tied to your organization — not arbitrary hosts on the internet.

Why Trust It

Built on the engine already testing production apps.

Vortex MCP isn't a new scanner bolted onto your editor. It's the same Vortex pentest engine that BestDefense runs against live applications — brought forward to the moment code is written, before it can ship.

Local-first: your traffic and source stay on your machine
Exploit-checked findings, not pattern matches
Contained by design: brain-free client, isolated container, scoped auth

Get started

Find the exploit before you commit it.

Start a free trial and run a real pentest against your local app from your editor — from Claude Code or any MCP client.

Runs on your machine · Docker required · blackbox or greybox.

Vortex MCP

Set up Vortex MCP