How to Use the Equixly MCP in Vercel AI SDK

Q: How do I handle Equixly authentication inside a Vercel AI SDK project?

You pass your Vinkius endpoint token to the createMCPClient transport configuration. The SDK manages the MCP connection over HTTP or SSE, so your Edge Functions can securely query listservices without exposing raw API keys to the client.

Q: Can I stream live Equixly scan progress using the Vercel AI SDK?

Yes, you can. By combining streamText with the getscan tool, your frontend displays active requests and discovered vulnerabilities in real time.

Stream Equixly API vulnerability data directly into your Next.js frontend with the Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Equixly to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream active pentest status directly to your UI

`trigger_scan` starts an automated penetration test against your target API while streaming live status updates back to your Vercel AI SDK frontend. Instead of staring at a generic loading spinner, your users watch live test results populate as the AI hunts down BOLA, injection, and broken authentication. You render this real-time progress using Edge Functions to ensure zero cold-starts, feeding active request counts and OWASP Top 10 mappings from the `get_scan` tool straight into your React components.

Upload API specifications from the browser

`upload_api_spec` takes raw OpenAPI, Postman, or GraphQL schemas and sends them straight to your Equixly target service. Your Vercel AI SDK application can render a drag-and-drop zone where developers drop their spec files, passing the content as a string directly to the MCP server. Once uploaded, your frontend updates on the fly by calling `list_api_specs` to show the active attack surface so developers can verify coverage before hitting run.

Build interactive security dashboards with the MCP Server

`get_scan_findings` extracts the exact HTTP requests, responses, and exploitation evidence for every vulnerability detected during a run. The Vercel AI SDK streams these findings directly into your UI, allowing developers to triage high-severity issues without waiting for a full report to compile. This lets you map raw exploits directly to clear remediation steps in your custom interface, while letting users clean up outdated targets on the fly by executing `delete_service` directly from their dashboard.

Setup guide

Set up Equixly MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Equixly tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Equixly transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You pass your Vinkius endpoint token to the `createMCPClient` transport configuration. The SDK manages the MCP connection over HTTP or SSE, so your Edge Functions can securely query `list_services` without exposing raw API keys to the client.

Yes, you can. By combining `streamText` with the `get_scan` tool, your frontend displays active requests and discovered vulnerabilities in real time.

Your frontend reads the file as a string and passes it to the `upload_api_spec` tool handler. The SDK routes this payload to the MCP server, which registers the spec format and updates the attack surface map instantly.

Yes, the Vinkius MCP client is fully compatible with Edge runtimes, letting you execute `list_scans` and trigger tests with minimal latency.

All OpenAPI schemas and vulnerability findings remain inside the V8 isolate sandbox on Vinkius. Your Vercel AI SDK backend communicates with Equixly over the MCP endpoint, ensuring that raw exploit evidence never touches public servers.

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