How to Use the Dixa MCP in Vercel AI SDK

Q: How do I stream Dixa conversation details using the Vercel AI SDK?

You call getconversationdetails inside your streamText tool configuration. The Vercel AI SDK handles the incoming JSON stream, rendering ticket updates live in your UI.

Q: How does Vercel AI SDK handle Dixa webhook updates using MCP?

The model uses listactivewebhooks to fetch your current event configurations. You can then map these events to your Vercel API routes to trigger live UI updates.

Get real-time Dixa support data streaming directly into your React components with 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 Dixa MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time ticket routing in Vercel AI SDK

The `assign_to_self` tool instantly claims an open ticket for the active agent, letting your Vercel AI SDK app update the UI state mid-stream. Instead of waiting for a full page refresh, your Dixa agent sees their ownership status change live inside the Vercel AI SDK stream. This direct feedback loop keeps your Dixa queue moving. You can also call `get_conversation_details` to pull the full ticket history directly into your Next.js chat interface. Because this MCP Server runs on Vinkius edge-compatible infrastructure, your Vercel AI SDK frontend gets sub-second responses without cold starts.

Live customer profile generation

The `create_customer_profile` tool builds a new user record in Dixa the moment your Vercel AI SDK chatbot collects their contact details. Your React frontend displays the newly created Dixa profile data inline, meaning agents don't have to jump back and forth between tabs. If the customer is already in your database, the Vercel AI SDK model uses `list_end_users` to pull up their historical Dixa records instantly. This MCP setup keeps your React UI populated with accurate Dixa customer context during live Vercel AI SDK chat sessions.

Close issues instantly via MCP Server tools

The `resolve_conversation` tool closes out resolved tickets immediately, updating your Vercel AI SDK dashboard state in real-time. Your support agents can trigger this action via voice or chat commands, and your Next.js UI immediately reflects the closed Dixa status. Before closing, the Vercel AI SDK model checks `get_connection_status` to ensure your Dixa API connection is green. This prevents silent failures and keeps your React frontend reporting accurate Dixa ticket metrics.

Setup guide

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

You call `get_conversation_details` inside your streamText tool configuration. The Vercel AI SDK handles the incoming JSON stream, rendering ticket updates live in your UI.

Yes. Your agent tells the UI to assign a ticket, and the model calls `assign_to_self` to update ownership instantly.

Yes, the Vinkius hosting layer runs this server in an isolated sandbox that plays perfectly with Edge runtimes. You can query `list_support_teams` or `list_support_agents` with zero cold-start latency.

The model uses `list_active_webhooks` to fetch your current event configurations. You can then map these events to your Vercel API routes to trigger live UI updates.

Your data stays private. Vinkius runs the server in an ephemeral sandbox, meaning your customer profiles and conversation histories are never stored on our servers. All API tokens are encrypted and used only to authenticate direct requests.

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