How to Use the Ocoya Social Media MCP in Vercel AI SDK

Q: How do I stream Ocoya Social Media post lists using the Vercel AI SDK?

You call mcpClient.tools() and pass them to streamText. Your agent will execute listposts and stream the raw post data directly to your frontend components. Remember to call mcpClient.close() when the session ends to free up resources.

Q: How does Vercel AI SDK handle authentication for the Ocoya Social Media MCP Server?

It uses the authProvider option during the client setup. This allows you to securely pass user credentials or OAuth tokens when calling endpoints like getme to verify the active user.

Q: How do I shut down the client connection properly?

Always invoke mcpClient.close() once your streaming text generation completes. This prevents hanging HTTP connections and keeps your serverless functions clean.

Pipe real-time social media data directly into your Next.js UI using Vercel AI SDK and the Ocoya MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Ocoya Social Media MCP to Vercel AI SDK

Create your Vinkius account to connect Ocoya Social Media to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Ocoya Social Media with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Instant UI updates for active workspaces

This MCP Server integration lets your Next.js app pull workspace details instantly without a spinning loading wheel. By calling `list_workspaces` and passing it to your streaming function, active accounts render on the screen as the model finds them. If a user wants to drill down, your agent uses `get_workspace` to grab specific metadata. The edge-compatible client processes these requests with zero cold-start lag, keeping your interface fast.

Real-time post auditing in the chat

This MCP Server allows your agent to fetch scheduled social queues directly inside a chat bubble. The SDK handles streaming text alongside tool outputs, meaning the agent can run `list_posts` and render the draft content line-by-line. When someone spots a typo, they can ask the agent to inspect the draft. The agent instantly calls `get_post` to show the full payload, letting the user verify the text and media links before they go live.

Live social profile mapping

This MCP Server lets your application query connected social accounts on the fly. The agent triggers `list_profiles` to map out every linked Instagram, LinkedIn, or Facebook account. For deep inspections, the agent runs `get_profile` to pull specific platform details. Because the Vercel AI SDK handles streaming tool calls, your users watch their brand network populate in real-time.

Setup guide

Set up Ocoya Social Media 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 Ocoya Social Media 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 Ocoya Social Media 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 Ocoya. 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 Ocoya Social Media 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 Ocoya Social Media MCP in Vercel AI SDK

You call `mcpClient.tools()` and pass them to `streamText`. Your agent will execute `list_posts` and stream the raw post data directly to your frontend components. Remember to call `mcpClient.close()` when the session ends to free up resources.

Yes. This integration is fully compatible with Edge runtimes. You can use `get_workspace` and `list_workspaces` inside your Next.js Edge routes to fetch workspace details without worrying about slow cold starts.

It uses the `authProvider` option during the client setup. This allows you to securely pass user credentials or OAuth tokens when calling endpoints like `get_me` to verify the active user.

Always invoke `mcpClient.close()` once your streaming text generation completes. This prevents hanging HTTP connections and keeps your serverless functions clean.

Your social profiles, posts, workspaces, and workflows are never stored on Vinkius servers. All requests pass through an ephemeral, zero-trust V8 sandbox that vaporizes your session data the microsecond the API call finishes.

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