How to Use the Modash MCP in Vercel AI SDK

Q: Can I stream Modash reports directly into Next.js components?

Yes, you pass gettiktokreport directly to streamUI or streamText. The Vercel AI SDK handles rendering the JSON payload as a React component as the data arrives.

Q: Can I search multiple platforms at the same time?

You can run searchinstagram and searchyoutube in parallel promises. The model coordinates both tools and merges the results into a single unified stream for your interface.

Feed real-time creator metrics directly into your React frontend using Vercel AI SDK and the Modash MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Modash MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Influencer Search in Vercel AI SDK

`search_instagram` feeds live search results straight into your streaming UI without making users wait for a full page reload. Your interface updates instantly as the model finds creators who match your target criteria. By passing this MCP tool directly to your `streamText` call, you bypass complex backend polling setups. The client renders raw profile cards the second the data hits the edge runtime.

On-the-Fly Demographic Reports

`get_youtube_report` pulls deep-audience metrics and dumps them into your frontend components in real time. Your users watch the demographic charts populate live instead of staring at a blank loading spinner. This tool extracts subscriber locations and viewer ages directly from the API. The Vercel AI SDK handles the stream chunking so your Edge Functions do not time out while processing large social profiles.

Instant Filter Matching

`list_interests` resolves niche category IDs instantly to refine your creator search queries before hitting the main networks. Your AI client matches user inputs to exact API taxonomy terms on the fly. Combining this with `list_locations` ensures your frontend application never sends malformed search parameters to the social platforms. You get clean, validated options mapped directly to the streaming UI.

Setup guide

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

Wrap your API calls in standard Vercel edge middleware or use the SDK's built-in retry logic. Because this MCP Server runs in Vinkius's isolated sandbox, you do not have to worry about managing raw credentials on the client side.

Yes, you pass `get_tiktok_report` directly to `streamUI` or `streamText`. The Vercel AI SDK handles rendering the JSON payload as a React component as the data arrives.

No, Vinkius handles the underlying authentication tokens for you. You only need one Vinkius endpoint token inside your environment variables to access all three social platforms.

You can run `search_instagram` and `search_youtube` in parallel promises. The model coordinates both tools and merges the results into a single unified stream for your interface.

This server never caches the raw influencer profiles or audience reports returned by `get_raw_profile`. All social data transits through Vinkius's ephemeral V8 sandboxes and is destroyed immediately after your streaming session closes.

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