How to Use the Anura MCP in Vercel AI SDK

Q: How do I install the Anura MCP Server inside a Vercel AI SDK project?

Run npm install ai @ai-sdk/mcp to get the required packages. Then initialize the client with createMCPClient pointing to the Vinkius endpoint, and pass the tools directly to your generative text functions.

Q: Can I stream the output of getsystemstatus using the Vercel AI SDK?

Yes, you can pass the tool directly to streamText. This allows your AI client to fetch the health status of the Anura fraud engine and render the progress directly to your React or Next.js frontend in real-time.

Stream real-time Anura ad fraud system status directly into your Next.js frontend using 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 Anura MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Fraud Status Streaming

The `get_system_status` tool lets your Vercel AI SDK app pull immediate operational metrics from Anura to verify that the fraud detection engine is active. Because the SDK streams responses directly, your users see live connection states and latency metrics load on their dashboard without waiting for a full page reload. You can feed this tool directly into `streamText` to build real-time monitoring widgets. When your security team asks your AI client if the fraud detection pipeline is healthy, the tool executes instantly and updates the React UI component frame by frame.

Zero-Lag Security Dashboards with MCP

Integrating the Anura MCP Server to run `get_system_status` with your Next.js Edge Functions means you can check system health on every inbound visitor routing. Running this status check inside an edge-compatible route prevents blocking the main thread while verifying that your anti-fraud endpoints are online. Calling `mcpClient.tools()` exposes the status check directly to your LLM, allowing it to decide whether to route traffic through backup verification paths if Anura reports an outage. The SDK handles the raw JSON payload and formats it for immediate consumption by your frontend components.

Clean Connection Lifecycle Management

Managing connections inside serverless environments requires strict cleanup, which is why your Vercel AI SDK setup relies on closing the transport channel immediately after checking Anura with `get_system_status`. Running this check inside a short-lived API route works best when you call `mcpClient.close()` right after the stream finishes. This prevents socket leaks in your Vercel deployments while ensuring your LLM can always pull fresh fraud-monitoring states. The SDK maps the tool output directly to your UI, keeping your serverless functions light and fast.

Setup guide

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

Run `npm install ai @ai-sdk/mcp` to get the required packages. Then initialize the client with `createMCPClient` pointing to the Vinkius endpoint, and pass the tools directly to your generative text functions.

Yes, you can pass the tool directly to `streamText`. This allows your AI client to fetch the health status of the Anura fraud engine and render the progress directly to your React or Next.js frontend in real-time.

No, you need to handle this manually in your code. Always call `mcpClient.close()` once your stream finishes to prevent hanging connections to the Anura API.

The SDK runs efficiently in edge runtimes, allowing you to trigger `get_system_status` with minimal overhead. This keeps your visitor validation pipeline fast and responsive even under heavy ad traffic.

Vinkius runs the server in an isolated sandbox, meaning your system status metrics and API keys are never exposed to the public. Only the final formatted tool output is sent to your Vercel AI SDK client over secure, encrypted transport.

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