How to Use the Coze MCP in Vercel AI SDK

Q: How do I list available Coze bots in Vercel AI SDK?

Call the listbots tool through your agent. It returns an array of published bots for a specific space ID, which you can map directly into your React components.

Stream Coze bot responses and RAG updates directly into your React or Next.js frontends using 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 Coze MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Coze chats through Vercel AI SDK

Your Next.js app needs live bot interactions without making users wait for a full response payload. By hooking this MCP Server into your Vercel AI SDK setup, text streams straight to the browser. Call `create_chat` inside a streamText function. When the bot needs a plugin, catch that state and pass the data back using `submit_tool_outputs`. The end user watches the answer type out live on screen.

Build live knowledge base uploads

Let your users feed data into a Coze Space straight from your React frontend. You don't need a heavy backend to handle the routing when this MCP setup connects directly to your edge functions. Wire up a file dropzone that triggers `upload_document`. The SDK streams the progress state back to the UI. You can then pull the updated list of collections using `list_datasets` to refresh the dashboard instantly.

Render available bots instantly

Creating a multi-bot interface means you need to know exactly what is published and available right now. Hardcoding bot IDs breaks the moment someone changes a setting in Coze. Fetch the live directory using `list_workspaces` and `list_bots`. The Vercel AI SDK can cache this response at the Edge, keeping your application fast while ensuring the UI always shows valid chat targets.

Setup guide

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

Install @ai-sdk/mcp and set up createMCPClient with your HTTP transport URL. Pass the result of mcpClient.tools() into your streamText call. Always remember to call mcpClient.close() when the route finishes.

Yes. When a bot requires external data, it pauses execution. Your application catches this state and runs submit_tool_outputs to resume the conversation stream.

The Vercel AI SDK handles the HTTP transport natively. You can run these tool calls directly from Edge routes without spinning up a Node.js server.

Call the list_bots tool through your agent. It returns an array of published bots for a specific space ID, which you can map directly into your React components.

Vinkius processes conversation logs and uploaded text documents in a V8 Isolate Sandbox. The environment is entirely ephemeral. Once your HTTP request closes, the memory dumps, leaving zero trace of your user interactions.

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