An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Equixly 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. Identify and audit API vulnerabilities through natural conversation.

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.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

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.

A futuristic MCP client docking bay
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 · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Equixly.

  1. 01

    Create service

    Register a new API target for autonomous pentesting by providing a name and base URL.

  2. 02

    Delete service

    Remove an API service and its entire scan history from Equixly.

  3. 03

    Get scan

    Retrieve a summary of a specific pentest, including request counts, endpoints explored, and OWASP mapping.

  4. 04

    List scans

    List all pentest sessions for a service, showing their status and detected vulnerability counts.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Equixly.

  1. 05

    List services

    Get a list of all registered API services, including their IDs and discovered endpoint counts.

  2. 06

    Upload API spec

    Upload OpenAPI, Postman, GraphQL, WSDL, or HAR specifications to expand the AI Hacker's attack surface.

  3. 07

    Get scan findings

    Download a list of exploitable vulnerabilities, including severity, HTTP methods, and remediation guidance.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Equixly.

  1. 08

    Get service

    Fetch the detailed configuration and metadata for a specific API service.

  2. 09

    List API specs

    List all API specifications currently uploaded to a specific service.

  3. 10

    Trigger scan

    Launch a new autonomous penetration test to hunt for BOLA, IDOR, and injection flaws.

Real work

What teams actually run

01

Post-Deployment Verification

Trigger a new scan immediately after a deployment to ensure no new vulnerabilities were introduced.

02

Continuous Security Monitoring

Register services with specific path-scoping rules to maintain a constant security baseline.

03

Rapid Vulnerability Remediation

Ask your agent for the specific exploitation evidence to validate that a security fix actually works.

04

API Surface Expansion

Upload updated GraphQL or OpenAPI specs to ensure the AI Hacker knows about new endpoints.

Automate a task

Put Equixly 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

Equixly 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.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

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

You don't need a client to put Equixly 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

908ms average. Fast in production.

Equixly is checked daily against the live service.

Daily averagePeak 1046ms
Oct 3Today
Fastest day
732ms
Slowest day
1046ms
14-day trend
Slowing+15%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 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 Equixly, so you can see the experience inside your AI.

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

Equixly Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_nyZHBp8MEawkoza3tzHMDtA3eBgX7w9c0cUuHFQx/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Equixly capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "equixly-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_nyZHBp8MEawkoza3tzHMDtA3eBgX7w9c0cUuHFQx/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 Equixly in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Equixly owners hand off.

This MCP is built for technical teams who need to integrate security testing into their existing development workflows.

  • 01

    Security Engineers

    They use the MCP to monitor security posture and trigger pentests without manual configuration.

  • 02

    Backend Developers

    They trigger scans upon deployment and pull remediation steps directly into their IDE.

  • 03

    DevSecOps Teams

    They use natural language to audit findings and integrate autonomous testing into CI/CD pipelines.

FAQ

Questions Equixly owners ask.

  • 01

    What kind of vulnerabilities does the Equixly AI Hacker look for?

    The AI Hacker specifically targets BOLA, IDOR, mass assignment, injection, broken authentication, and business logic flaws.

  • 02

    Which API specifications can I upload?

    You can upload OpenAPI (JSON/YAML), Postman, GraphQL, WSDL, and HAR files to define your attack surface.

  • 03

    Can I use this in my IDE?

    Yes, you can connect this MCP to any compatible client like Cursor or VS Code to manage security while you code.

  • 04

    How do I know if a vulnerability is real?

    The MCP provides detailed findings that include request and response evidence of exploitation to help you validate each flaw.

  • 05

    Is the testing process manual?

    No, once you trigger a scan, the process is autonomous. The AI Hacker explores the endpoints and attempts attacks on its own.

  • 06

    Can my agent trigger an autonomous penetration test on a specific API?

    Yes. Use the 'trigger_scan' capability with the target Service ID. The Equixly AI Hacker will begin an autonomous session, learning and attacking the API for various flaws including BOLA and business logic errors.

  • 07

    How do I see the security vulnerabilities found in the last scan via chat?

    Use the 'get_scan_findings' capability. Provide the Service and Scan IDs. The agent will retrieve a detailed list of confirmed security flaws, including severity levels and actionable remediation guidance.

  • 08

    Can I upload an OpenAPI specification to improve scan coverage through the agent?

    Absolutely. Use the 'upload_api_spec' capability. Provide the spec content and format (e.g., 'openapi'). This allows the AI Hacker to understand the full attack surface and maximize vulnerability discovery.

Explore

More in Developer Tools

Suggestions

Connect Equixly to Claude, Cursor, ChatGPT & more