How to Use the Decodo (Smartproxy) MCP in Vercel AI SDK

Q: Can I build a real-time bandwidth monitor for Decodo (Smartproxy) with the Vercel AI SDK?

Yes, that's a perfect use case. Your agent would call the gettrafficusage tool. The Vercel AI SDK streams the response, allowing you to update a chart or graph in your UI without a page refresh.

Q: Is this hard to set up?

Not at all. You just install the @ai-sdk/mcp package and point the client to your Vinkius endpoint URL. The tools are then available to your generateText calls.

Q: Can I see all my proxy configurations?

You can. Your agent can use listdatacenterproxies, listdedicatedproxies, and listresidentialproxies to pull all your different proxy setups. The AI SDK makes it easy to display this info in your app.

Build real-time proxy management UIs. Stream Decodo stats directly into your Next.js app 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 Decodo (Smartproxy) MCP to Vercel AI SDK

Create your Vinkius account to connect Decodo (Smartproxy) 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 Decodo (Smartproxy) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Proxy Status in Your UI

This MCP Server connects your Vercel AI SDK app to your Decodo account. You can build dashboards that show proxy status and usage without making your users wait. The data just streams right into your React components. For instance, call `get_traffic_usage` and watch bandwidth stats update in real-time. Or use `list_residential_proxies` to populate a dynamic list of available endpoints, letting users see options appear live on their screen. No more spinners.

Build Your Own Decodo Dashboard

Stop logging into the Decodo website for basic info. With the Vercel AI SDK, you can build a custom front-end that pulls all your account data. Your agent can fetch account details, subscription status, and sub-user lists on command. Just ask your agent to `get_account_details` or `list_subscriptions` and the results stream directly into your UI. It's perfect for creating internal tools that give your team exactly the information they need, right where they're working.

Interactive Scraping Stats via MCP Server

Connect your agent to the Decodo (Smartproxy) scraper APIs. This lets you build tools that monitor your scraping jobs directly from your own application. You can use the `get_scraper_stats` tool to feed data into a live chart or table. Your users can see success rates and data usage update as it happens, all powered by the AI SDK's streaming capabilities.

Setup guide

Set up Decodo (Smartproxy) 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 Decodo (Smartproxy) 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 Decodo (Smartproxy) 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 Decodo (Smartproxy). 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 Decodo (Smartproxy) 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 Decodo (Smartproxy) MCP in Vercel AI SDK

You connect the MCP client in your Next.js or React app, then pass the Decodo tools to `generateText` or `streamText`. The AI SDK handles calling the tool and streaming the proxy data right back into your UI components.

Yes, that's a perfect use case. Your agent would call the `get_traffic_usage` tool. The Vercel AI SDK streams the response, allowing you to update a chart or graph in your UI without a page refresh.

Not at all. You just install the `@ai-sdk/mcp` package and point the client to your Vinkius endpoint URL. The tools are then available to your `generateText` calls.

You can. Your agent can use `list_datacenter_proxies`, `list_dedicated_proxies`, and `list_residential_proxies` to pull all your different proxy setups. The AI SDK makes it easy to display this info in your app.

Your Vinkius endpoint token is the only credential needed. All requests are ephemeral and touch only your Decodo proxy configurations and usage statistics. The server runs in a zero-trust sandbox, so your account data stays isolated.

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