How to Use the CometChat MCP in Vercel AI SDK

Q: Can my Vercel AI SDK agent create user accounts in CometChat?

Yes. Your agent can call createuser dynamically based on user input, instantly registering new users in your database.

Q: How do I fetch user lists using CometChat and Vercel AI SDK?

Your agent calls listusers to pull the active directory. The JSON output streams straight to your frontend component for instant rendering.

Let your Vercel AI SDK frontend stream real-time CometChat updates and group management directly to your React components.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CometChat MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Chat Moderation via Vercel AI SDK

Your React UI shouldn't hang while your agent cleans up chat rooms. This MCP integration lets you invoke `deactivate_user` or `delete_user` instantly inside edge functions. The results stream straight to the browser, updating your administrative dashboard without annoying loading spinners. If a user behaves badly, your agent grabs their profile details using `get_user`. It checks the context, decides on the action, and executes the suspension. Your interface updates live while the agent works.

Dynamic Group Provisioning in Next.js

Building collaborative spaces on the fly usually requires writing custom api routes. With this MCP Server, your agent calls `create_group` directly during a streamText loop. It sets up the chat room based on the user's conversation context. Once the group exists, the agent can immediately run `get_group_details` to verify the setup. It then feeds the metadata back into the Vercel AI SDK stream, letting the user join the new channel within milliseconds.

Real-time Message History Ingestion

Fetching past conversations shouldn't block your user interface. By calling `list_messages`, your agent pulls recent logs to catch up on context before generating replies. It keeps the context window fresh without manual database queries. You can also use `send_message` to dispatch automated responses back into the channel. The SDK handles the streaming output, making sure the user sees the agent's progress as it types out the message.

Setup guide

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

Initialize the client using the Vinkius endpoint token. Then, grab the tools from the MCP client and pass them directly into your streamText tool call configuration.

Yes. Your agent can call `create_user` dynamically based on user input, instantly registering new users in your database.

Yes, the connection runs over lightweight protocols. This makes it fully compatible with Vercel Edge Functions without hitting execution limits.

Your agent calls `list_users` to pull the active directory. The JSON output streams straight to your frontend component for instant rendering.

All chat logs and user details are handled inside an isolated sandbox. The MCP protocol ensures your raw tokens and conversation transcripts never persist on third-party servers.

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