How to Use the Kitetags MCP in Vercel AI SDK

Q: How do I connect the Kitetags MCP server to my Vercel AI SDK project?

Install the required packages via npm, then use createMCPClient pointing to your Vinkius HTTP endpoint. This MCP setup passes the client tools directly into your generateText or streamText calls. Always close the client connection when the execution finishes.

Q: What tools are available for clean-up operations?

You have complete control over your taxonomy with deletetag and deletegroup. Your agent runs these cleanup tasks automatically when analytics show a tag group is no longer driving impressions.

Feed real-time TikTok and Instagram tag analytics directly into your Next.js frontend with 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 Kitetags MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream hashtag discovery to the UI with Vercel AI SDK

The `search_tags` tool finds high-performing Instagram and TikTok hashtags on demand. Instead of waiting for a slow API response to resolve behind a loading spinner, your Vercel AI SDK setup streams these recommendations straight to your user interface. This means you build snappy, interactive dashboards where creators see tag ideas pop up line by line. You just feed the tool output into `streamText` to keep your frontend fast and responsive.

Track tag performance metrics on the edge

The `get_tag_analytics` tool pulls hard numbers on reach, engagement, and trend velocity. Because this MCP Server runs on Vinkius, your Edge Functions fetch these metrics without choking on cold starts or heavy runtimes. You feed this data directly into your streaming UI components. Your users get immediate visibility into which tags are actually driving views right now, bypassing stale database lookups.

Organize social campaigns programmatically

The `create_group` tool builds structured categories to organize your social media campaigns. Your agent uses this along with `list_group_tags` to group high-performing assets together without manual database mapping. It allows your app to dynamically sort trending hashtags based on real-time performance. When a trend dies, your agent calls `delete_tag` or `delete_group` to keep your active campaigns clean.

Setup guide

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

Install the required packages via npm, then use `createMCPClient` pointing to your Vinkius HTTP endpoint. This MCP setup passes the client tools directly into your `generateText` or `streamText` calls. Always close the client connection when the execution finishes.

Yes. The server handles external API requests and passes structured metrics back to your agent. This lets your edge middleware run light, offloading the heavy lifting of trend analysis to the managed instance.

The MCP protocol returns structured data that the SDK consumes as tool calls. Your frontend renders these tool states immediately, allowing users to watch the agent find, organize, and group tags live.

You have complete control over your taxonomy with `delete_tag` and `delete_group`. Your agent runs these cleanup tasks automatically when analytics show a tag group is no longer driving impressions.

We never touch your private account credentials or direct login details. Kitetags only processes public hashtag metrics, trend data, and the custom tag groups you create, all isolated in a secure V8 sandbox on Vinkius.

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