How do I connect my Halo Security account?

You subscribe to the MCP on Vinkius and enter your Halo Security API Key. Once connected, your AI client can immediately start using the capabilities.

Which AI clients can I use with this MCP?

You can use any MCP-compatible client, including Claude, Cursor, and Windsurf.

Can I trigger new scans through my AI agent?

Yes, you can use the trigger_scan capability to start a new security assessment for any target via your chat interface.

Does this MCP replace the Halo Security dashboard?

It doesn't replace it, but it acts as a functional interface so you don't have to manually export reports or click through menus to get data.

What kind of assets can I monitor?

You can add and monitor various targets including domains, IP addresses, and applications.

How do I find my Halo Security API Key?

Log in to your Halo Security account, navigate to Account Settings and then to the API section. You will be able to generate and copy your unique API key from there.

Can I trigger a new scan through this integration?

Yes! Use the trigger_scan capability by providing the unique target ID of the asset you want to assess. Halo Security will initiate the scan immediately.

How are security issues categorized?

Issues are categorized by their severity (e.g., Critical, High, Medium, Low) and type (e.g., Vulnerability, Information, SSL Issue). You can use list_issues to see all findings.

Is it possible to add new domains to monitor?

Yes, the add_target capability allows you to add new domains or IP addresses to your security perimeter directly from the AI agent.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Halo Security to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Control your security posture through a single chat interface.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 11 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 11 available through Halo Security.

01
List certificates
This capability pulls a list of SSL/TLS certificates and their current status.
02
List scans
Use this to view the history of all completed security scans.
03
List targets
This capability returns a list of all assets currently being monitored.
04
List technologies
Get a list of the specific technologies and libraries detected on your targets.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 11 available through Halo Security.

05
List open ports
This capability identifies all open ports discovered across your monitored assets.
06
Add target
Use this to add a new domain, IP, or app to your security monitoring perimeter.
07
Get security risk
This capability retrieves your overall security risk scores and recent trends.
08
List dns records
Access the DNS records that were found during the reconnaissance phase.

Capability set03 / 03

09-11

3 capabilities in this set.

Part of 11 available through Halo Security.

09
List issues
This capability provides a list of all discovered security issues and vulnerabilities.
10
Trigger scan
Use this to start a new on-demand security assessment for a specific target.
11
Get issue
This capability fetches deep technical details for a specific security issue.

Real work

What teams actually run

Rapid Triage

A security engineer asks the agent to list all high severity issues to prioritize fixes.

Continuous Monitoring

A DevSecOps engineer monitors risk score trends to ensure security posture stays stable.

Asset Onboarding

You add a new domain to your monitoring perimeter using a simple text command.

Infrastructure Audits

An engineer checks for open ports or outdated libraries across all active targets.

Automate a task

Put Halo Security to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Halo Security works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Halo Security to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

943ms average. Fast in production.

Halo Security is checked daily against the live service.

Daily averagePeak 1265ms

Oct 3Today

Fastest day: 753ms
Slowest day: 1265ms
14-day trend: Improving-20%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 11 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Halo Security, so you can see the experience inside your AI.

It does not authenticate your account with Halo Security. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Halo Security Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_hixg6FCgdmM8eEwHlXEHXuQOZBhHWU8M7N1KuKeO/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Halo Security capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "halo-security-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_hixg6FCgdmM8eEwHlXEHXuQOZBhHWU8M7N1KuKeO/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Halo Security in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Halo Security owners hand off.

This MCP is built for technical teams managing large, evolving attack surfaces.

01
Security Engineers
They use the agent to pull asset lists and vulnerability details during triage.
02
DevSecOps Teams
They automate scan triggers and real-time issue monitoring.
03
CISOs
They use the agent to get high-level risk scores and posture trends.

FAQ

Questions Halo Security owners ask.

01
How do I connect my Halo Security account?
You subscribe to the MCP on Vinkius and enter your Halo Security API Key. Once connected, your AI client can immediately start using the capabilities.
02
Which AI clients can I use with this MCP?
You can use any MCP-compatible client, including Claude, Cursor, and Windsurf.
03
Can I trigger new scans through my AI agent?
Yes, you can use the trigger_scan capability to start a new security assessment for any target via your chat interface.
04
Does this MCP replace the Halo Security dashboard?
It doesn't replace it, but it acts as a functional interface so you don't have to manually export reports or click through menus to get data.
05
What kind of assets can I monitor?
You can add and monitor various targets including domains, IP addresses, and applications.
06
How do I find my Halo Security API Key?
Log in to your Halo Security account, navigate to Account Settings and then to the API section. You will be able to generate and copy your unique API key from there.
07
Can I trigger a new scan through this integration?
Yes! Use the trigger_scan capability by providing the unique target ID of the asset you want to assess. Halo Security will initiate the scan immediately.
08
How are security issues categorized?
Issues are categorized by their severity (e.g., Critical, High, Medium, Low) and type (e.g., Vulnerability, Information, SSL Issue). You can use list_issues to see all findings.
09
Is it possible to add new domains to monitor?
Yes, the add_target capability allows you to add new domains or IP addresses to your security perimeter directly from the AI agent.

Explore

More in Cloud Infrastructure

Connect Halo Security to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

List certificates

List scans

List targets

List technologies

05-08

List open ports

Add target

Get security risk

List dns records

09-11

List issues

Trigger scan

Get issue

What teams actually run

Rapid Triage

Continuous Monitoring

Asset Onboarding

Infrastructure Audits

Building your own app? The connector is yours to use.

Halo Security Connector

Claude Desktop

Security Engineers

DevSecOps Teams

CISOs

How do I connect my Halo Security account?

Which AI clients can I use with this MCP?

Can I trigger new scans through my AI agent?

Does this MCP replace the Halo Security dashboard?

What kind of assets can I monitor?

How do I find my Halo Security API Key?

Can I trigger a new scan through this integration?

How are security issues categorized?

Is it possible to add new domains to monitor?

Aikido Security AI Connector

Patchstack Security AI Connector

Contrast Security AI Connector

Lacework (Cloud Security & CNAPP) AI Connector

Suggestions

Salt Security AI Connector

Intruder AI Connector

HackEDU (Security Journey) AI Connector

HCL AppScan AI Connector