How to Use the Anthropic Alternative MCP in Vercel AI SDK

Q: How do I set up the Anthropic Alternative with Vercel AI SDK?

Install the packages and initialize the MCP client using createMCPClient with the Vinkius URL. Then, feed the tools directly into your streamText call. Don't forget to call close() on the client when the stream finishes.

Q: How do I handle user approvals for Claude batch runs?

You can intercept the createbatchmessage tool call in your Next.js middleware. Prompt the user for confirmation in your UI before sending the batch payload to the Vinkius endpoint.

Get Claude responses streaming straight to your React UI in real-time using Vercel AI SDK and this Anthropic Alternative.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Anthropic Alternative MCP to Vercel AI SDK

Create your Vinkius account to connect Anthropic Alternative 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 Anthropic Alternative with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Claude streaming with Vercel AI SDK

The `send_message` tool connects your Vercel AI SDK setup directly to Claude models like Claude 3.5 Sonnet. Instead of making your users stare at a blank screen, this tool streams raw text chunks directly to your React or Next.js frontend as they generate. You configure this by passing the MCP client tools directly into `streamText`. The SDK handles the edge-runtime connection, letting your UI render the incoming Claude tokens instantly without intermediate API glue.

On-the-fly token counting before you send

The `count_tokens` tool lets your Vercel AI SDK application check prompt sizes before firing off expensive API requests. This keeps your MCP integration fast and avoids unexpected billing surprises on large payloads. Integrating this directly into your Next.js server actions keeps costs predictable. Your UI can warn users they are over the limit before they hit send, saving both latency and API budget on heavy Claude queries.

Bulk prompt processing via Claude batches

The `create_batch_message` tool lets you offload massive, non-urgent background tasks from your Vercel AI SDK edge functions. When a user uploads a massive dataset, you can bundle the prompts and dispatch them in a single batch to save fifty percent on API costs. Use `get_batch_message` within a polling route or background cron to track the status. This keeps your edge functions from hitting execution limits while waiting for hours of Claude processing to finish.

Setup guide

Set up Anthropic Alternative 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 Anthropic Alternative 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 Anthropic Alternative 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 Anthropic. 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 Anthropic Alternative 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 Anthropic Alternative MCP in Vercel AI SDK

Install the packages and initialize the MCP client using `createMCPClient` with the Vinkius URL. Then, feed the tools directly into your `streamText` call. Don't forget to call `close()` on the client when the stream finishes.

Yes. Because this server runs on Vinkius, your edge code only makes a lightweight HTTP call. This avoids the heavy Node.js dependencies that usually break strict edge runtimes.

This MCP Server gives your Vercel AI SDK app direct access to tools like `list_models` dynamically. Your UI can update its model dropdown automatically when Anthropic drops a new Claude version, without you redeploying code.

You can intercept the `create_batch_message` tool call in your Next.js middleware. Prompt the user for confirmation in your UI before sending the batch payload to the Vinkius endpoint.

Your Anthropic API keys and raw prompt text are processed in isolated memory blocks on Vinkius. They are never logged or cached, keeping your secure keys isolated from the public internet.

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