How to Use the Geekflare MCP in Vercel AI SDK

Q: How do I use Geekflare with the Vercel AI SDK to check for broken links?

Connect the Geekflare MCP server to your createMCPClient instance. Your agent can then call the checkbrokenlinks tool. The AI SDK will stream the list of broken URLs directly into your UI component as they are discovered.

Q: What's the best way to show load times with the Geekflare MCP Server and the Vercel AI SDK?

Use the measureloadtime tool. Your agent requests the audit, and the TTFB and other speed metrics are streamed back. This lets you display performance data instantly in your Next.js or React application without waiting for the full report.

Q: How is my data handled when I use the Geekflare MCP server to check a website's SSL certificate?

When you use the scanssltlscert tool, the target domain name is sent to the Geekflare server. The server performs the scan, and the certificate details are returned. Vinkius processes this data in an ephemeral, zero-trust environment, and it is not stored after your request is complete.

Stream Geekflare's site audit results directly into your React UI with the Vercel AI SDK. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Geekflare MCP to Vercel AI SDK

Create your Vinkius account to connect Geekflare 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 Geekflare with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Site Audits in Your UI

Let your users enter a URL and watch a full site audit happen in real time. With the Vercel AI SDK, you can stream results from Geekflare tools like `run_lighthouse_audit` and `measure_load_time` directly into your React components. Performance scores, metrics, and warnings appear as they're generated, not after a long wait. This turns a static report into an interactive diagnostic tool. You can build a security dashboard that populates live as `scan_ssl_tls_cert` checks your certificate chain or `get_dns_records` verifies your configuration. The streaming responses show your AI client is working, which builds trust and keeps users engaged.

Visual & Link Integrity Checks

Combine visual checks with data validation. Your agent can call `take_website_screenshot` and `check_broken_links` in the same request. The AI SDK lets you render the screenshot as it arrives while simultaneously listing out any 404s the tool discovers on the page. This isn't just for one-off checks. Build a continuous monitoring dashboard inside your own product. An agent, powered by the AI SDK, can periodically run these checks on key pages. It then streams any broken link alerts or visual changes directly to a live-updating dashboard for your team to see.

Build with the Vercel AI SDK

Your agent gets access to all seven Geekflare tools out of the box. When your frontend calls `streamText`, the data from tools like `get_whois_data` doesn't come back as a single, large JSON blob. The results stream in, which lets you update your UI piece by piece. This makes for a much better user experience. Instead of a blank screen and a spinner, users see the audit happening. This MCP server gives your UI the raw data to show progress, turning a boring wait into an interesting process.

Setup guide

Set up Geekflare 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 Geekflare 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 Geekflare 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 Geekflare. 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 Geekflare 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 Geekflare MCP in Vercel AI SDK

Connect the Geekflare MCP server to your `createMCPClient` instance. Your agent can then call the `check_broken_links` tool. The AI SDK will stream the list of broken URLs directly into your UI component as they are discovered.

Yes. Once your MCP server is configured, your agent can invoke `run_lighthouse_audit`. The Vercel AI SDK's streaming capabilities mean you can build a UI that shows Lighthouse scores and metrics updating in real-time as the audit runs.

Use the `measure_load_time` tool. Your agent requests the audit, and the TTFB and other speed metrics are streamed back. This lets you display performance data instantly in your Next.js or React application without waiting for the full report.

Yes, the Vercel AI SDK is fully compatible with edge functions. You can run your Geekflare-powered agent on the edge for low-latency responses when triggering tools like `get_dns_records` or `measure_load_time`.

When you use the `scan_ssl_tls_cert` tool, the target domain name is sent to the Geekflare server. The server performs the scan, and the certificate details are returned. Vinkius processes this data in an ephemeral, zero-trust environment, and it is not stored after your request is complete.

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