How to Use the Equixly MCP in Mastra AI

Q: How do I register the Equixly MCP server inside Mastra AI?

You instantiate MCPClient with your Vinkius endpoint URL and add it to your Mastra agent's tools array. The framework automatically registers tools like triggerscan and getscanfindings for your workflows.

Q: How do I implement human-in-the-loop approval before deleting an Equixly service in Mastra AI?

You set requireToolApproval to true on the Mastra agent configuration for the deleteservice tool. This pauses the workflow and prompts an administrator before permanently erasing the service and its history.

Q: Can I run multiple parallel pentests across different environments?

Yes. Your agent can query listservices and trigger parallel runs of triggerscan for each distinct base URL, handling the concurrent states within your TypeScript workflow.

Run autonomous API security workflows with Mastra AI and Equixly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Equixly MCP to Mastra AI

Create your Vinkius account to connect Equixly to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Equixly with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Equixly scans with Mastra AI workflows

`trigger_scan` kicks off an autonomous pentest that Mastra AI monitors using built-in retry logic and exponential backoff. If a scan fails or times out due to network instability, the workflow engine automatically retries the operation without crashing your agent. You can build conditional paths that check `get_scan` status at regular intervals, branching to alert your team if the scan completes with critical vulnerabilities.

Keep target services in sync automatically

`list_services` retrieves all registered API targets so your Mastra AI agent can audit them against your actual cloud deployment state. If a service is missing, the agent runs `create_service` with the live base URL to register the new target instantly. This setup ensures your security testing map always mirrors your production environment, allowing the agent to clean up decommissioned environments by executing `delete_service` over the MCP link when a branch is merged.

Update API schemas using the Mastra AI MCP Server

`upload_api_spec` updates your target's attack surface whenever your Mastra AI agent detects a change in your codebase repository. The agent fetches the latest OpenAPI or Postman spec, checks it against `list_api_specs`, and uploads the new version as a raw string. This automation guarantees that your autonomous pentester always attacks the latest endpoints, avoiding the common pitfall of running tests against outdated schemas.

Setup guide

Set up Equixly MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Equixly tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "equixly-mcp-client",
  servers: {
    "equixly-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Equixly Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Equixly tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Equixly transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Equixly. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Equixly now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Equixly MCP in Mastra AI

You instantiate `MCPClient` with your Vinkius endpoint URL and add it to your Mastra agent's tools array. The framework automatically registers tools like `trigger_scan` and `get_scan_findings` for your workflows.

Yes, you can configure your Mastra workflow to catch errors from `trigger_scan` and retry. The engine handles the backoff timing while checking `get_scan` to verify when the run succeeds.

You set `requireToolApproval` to true on the Mastra agent configuration for the `delete_service` tool. This pauses the workflow and prompts an administrator before permanently erasing the service and its history.

Yes. Your agent can query `list_services` and trigger parallel runs of `trigger_scan` for each distinct base URL, handling the concurrent states within your TypeScript workflow.

Your OpenAPI specs and scan findings are processed in memory within the Vinkius V8 sandbox. Mastra AI only receives the raw text payloads over secure MCP SSE connections, keeping your vulnerability evidence isolated from external logs.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript