How to Use the Beagle Security MCP in Vercel AI SDK

Q: How do I connect Beagle Security to my Vercel AI SDK app?

Install the @ai-sdk/mcp package and use createMCPClient to point to the Vinkius endpoint. Pass the tools directly to streamText to let your agent trigger scans.

Q: Can I stream live security test results with Beagle Security and Vercel AI SDK?

Yes, your agent uses getteststatus and gettestresult to pull live data. Because of how the SDK handles tool calls, the raw JSON results stream into your UI components without blocking.

Run web vulnerability scans and stream live security test results directly into your Vercel AI SDK frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Beagle Security MCP to Vercel AI SDK

Create your Vinkius account to connect Beagle Security 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 Beagle Security with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live security test status to your UI

The `get_test_status` tool lets your Vercel AI SDK application check on active vulnerability scans in real-time. Instead of making users stare at a static page or wait for a full page reload, you can stream the current progress of your Beagle Security scans directly into your React or Next.js components. Combined with `get_running_tests`, your AI client triggers these status checks dynamically as the scan runs. The streaming interface displays live status updates line-by-line, giving developers immediate feedback on their security posture without API polling lag.

Map web vulnerabilities using this MCP Server

The `get_test_result` tool pulls raw JSON payloads containing detailed vulnerability data directly into your edge-rendered Vercel AI SDK setup. Your agent reads the raw scan data and instantly parses the critical vulnerabilities for the user. By calling `list_applications` alongside this, the agent maps specific security threats to the corresponding web apps. The user gets a live-rendered breakdown of security issues without waiting for a backend server to process the report.

Trigger security scans directly from your frontend

The `start_test` tool initiates a fresh penetration test on your configured web applications. Users can click a button in your Next.js app, prompting the Vercel AI SDK to call this tool and spin up a scan immediately. If a test goes off the rails or needs to be aborted, `stop_test` terminates the active run. This gives your interface complete control over the Beagle Security API, handled entirely within edge-compatible routes.

Setup guide

Set up Beagle Security 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 Beagle Security 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 Beagle Security 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 Beagle Security. 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 Beagle Security 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 Beagle Security MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package and use `createMCPClient` to point to the Vinkius endpoint. Pass the tools directly to `streamText` to let your agent trigger scans.

Yes, your agent uses `get_test_status` and `get_test_result` to pull live data. Because of how the SDK handles tool calls, the raw JSON results stream into your UI components without blocking.

The server runs on Vinkius, meaning your edge functions only need to make a lightweight HTTP call. You avoid heavy SDK dependencies in your edge runtime by using this clean MCP client.

The tool sends a request to Beagle Security to kick off a new vulnerability scan. Your agent will receive confirmation and can then poll `get_test_status` to show the user the test is running.

Your raw vulnerability reports and application details never touch Vinkius disks. All JSON data retrieved via `get_test_result` is proxied securely through an ephemeral sandbox and passed directly to your Vercel AI SDK client.

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