How to Use the Curator.io MCP in Vercel AI SDK

Q: How do I handle token expiration when using Curator.io with the Vercel AI SDK?

You can configure the authProvider option in your MCP client setup to refresh credentials on the fly. This keeps your Edge Functions authenticated without hardcoding expiring keys in your Next.js environment variables.

Q: Can I stream Curator.io post counts to a React frontend using Vercel AI SDK?

Yes, you can pipe the output of getfeedpostcount directly through the streamText function. This allows the AI to output live metrics directly into your UI skeleton without making the user wait for a full page reload.

Q: What is the best way to clean up Curator.io connections in Vercel AI SDK?

Always call mcpClient.close() inside your API route or server action once the text generation completes. This prevents hanging HTTP connections from consuming your Vercel concurrent execution limits.

Q: How do I search active social feeds with this setup?

Pass the searchpostsinfeed tool to your generateText call. The agent will parse the user's prompt, extract the search keywords, and fetch matching results from the API.

Render live social feeds directly into your React components without loading spinners using Curator.io and 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 Curator.io MCP to Vercel AI SDK

Create your Vinkius account to connect Curator.io 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 Curator.io with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Social Dashboards in Vercel AI SDK

Using `list_feed_posts` and `get_feed_post_count` lets your frontend display social content without waiting for heavy API payloads to resolve. Your React or Next.js app renders social media posts as the AI client fetches them. Integrating this with Edge Functions is straightforward since the Vercel AI SDK handles the MCP HTTP transport natively. You just initialize the client, call the tool, and watch the feed metadata populate on the screen instantly.

Live Moderation Rule Inspection

With `list_moderation_rules`, your AI agent instantly queries active keyword exclusions when users ask to audit their filters. This MCP Server lets it bypass manual admin panel checks entirely. You can quickly display these rules alongside the active post list retrieved by `search_posts_in_feed`. The UI updates live as the agent runs the search, giving your team immediate visual feedback on their moderation settings.

Display Connected Accounts Instantly

Calling `list_social_connections` lets your custom dashboard display active social connections directly inside the streaming runtime. Users see their connected Instagram or Twitter profiles appear in the chat interface as soon as the agent verifies the connection status. If a feed goes dark, the agent uses `list_feed_sources` to pinpoint which specific API token or handle is causing the issue. This rapid feedback loop helps non-technical team members troubleshoot connection issues without opening a support ticket.

Setup guide

Set up Curator.io 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 Curator.io 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 Curator.io 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 Curator.io. 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 Curator.io 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 Curator.io MCP in Vercel AI SDK

You can configure the `authProvider` option in your MCP client setup to refresh credentials on the fly. This keeps your Edge Functions authenticated without hardcoding expiring keys in your Next.js environment variables.

Yes, you can pipe the output of `get_feed_post_count` directly through the `streamText` function. This allows the AI to output live metrics directly into your UI skeleton without making the user wait for a full page reload.

Always call `mcpClient.close()` inside your API route or server action once the text generation completes. This prevents hanging HTTP connections from consuming your Vercel concurrent execution limits.

Pass the `search_posts_in_feed` tool to your `generateText` call. The agent will parse the user's prompt, extract the search keywords, and fetch matching results from the API.

All API credentials and social media feed data are processed in an isolated V8 sandbox on Vinkius. Your private feed content and moderation rules are never stored or used to train public models, keeping your social data private.

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