How to Use the Beekeeper MCP in Vercel AI SDK

Q: How do I use the Vercel AI SDK to list all Beekeeper streams?

Your agent calls the liststreams tool. The Vercel AI SDK will stream the results, which you can then map into a list in your React or Svelte component. It's a single tool call.

Q: Can my agent send direct messages in Beekeeper using the Vercel AI SDK?

Yes, that's what the sendmessage tool is for. Your agent passes the user ID and message content, and the MCP server handles it. You can build a simple messaging interface around this.

Q: What's the setup for connecting the Vercel AI SDK to this Beekeeper MCP?

It's quick. Install @ai-sdk/mcp, create the client with your Vinkius endpoint URL, and pass the tools to generateText. Just remember to call mcpClient.close() to terminate the connection when you're done.

Stream Beekeeper posts, messages, and user lists directly into your UI components with the Vercel AI SDK. No loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Beekeeper MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Beekeeper Dashboards

This toolset lets your agent pull live data from Beekeeper streams and conversations. Use `list_posts` to watch a stream update in real-time or `list_messages` to build a live chat view right inside your Next.js application. Because the Vercel AI SDK streams tool results, your users see the data as it arrives. You can build components that populate with Beekeeper posts or user profiles instantly, creating a much more responsive feel than traditional API calls. It's perfect for admin panels or communication hubs.

Manage Users with Your Beekeeper MCP Server

Give your support team an interface to manage the Beekeeper user base. Your agent can use `list_users` to populate a table, `search_users` to find someone specific, and `get_user` to pull up their full details. Connect these tools to a simple form, and your agent handles the logic. It's a fast way to build internal tools without writing a full backend. The user types a name, the agent calls the tool, and the profile appears on screen.

Post to Streams from Any App

Let your users create Beekeeper content without leaving your application. The `create_post` tool lets an agent take user input—from a simple text field or a complex form—and publish it directly to a specified stream. You can also have the agent `send_message` for direct communication. This turns any part of your UI into a potential Beekeeper client, all wired up through your agent and this MCP server.

Setup guide

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

Your agent calls the `list_streams` tool. The Vercel AI SDK will stream the results, which you can then map into a list in your React or Svelte component. It's a single tool call.

Yes, that's what the `send_message` tool is for. Your agent passes the user ID and message content, and the MCP server handles it. You can build a simple messaging interface around this.

It's quick. Install `@ai-sdk/mcp`, create the client with your Vinkius endpoint URL, and pass the tools to `generateText`. Just remember to call `mcpClient.close()` to terminate the connection when you're done.

An MCP server exposes tools for an AI agent, not just endpoints. Your agent understands what `search_users` does, so you can just ask it 'find the user named John Doe' instead of formatting a specific HTTP request.

The server only touches the data required by the tools you invoke, like user profiles, post content, and direct messages. Your Vinkius endpoint is sandboxed and ephemeral, so each session is isolated. No data is stored long-term.

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