How to Use the Uniphore Conversation AI MCP in Vercel AI SDK

Q: How do I search meetings using Uniphore Conversation AI and Vercel AI SDK?

First, use listmeetings to get all available IDs. Then, call searchmeetings, passing the keyword or topic you need. The results populate in your client immediately.

Q: Does Uniphore Conversation AI support streaming analytics with Vercel AI SDK?

Yeah, it does. You can use getmeetinganalytics and stream the insights directly into your UI using the Vercel AI SDK. It keeps the user engaged because the data appears live.

Q: What kind of meetings can Uniphore Conversation AI help summarize with Vercel AI SDK?

You can get summaries for any meeting ID retrieved using getmeeting. The summary is streamed, so your user sees the text appear piece by piece in the client.

Q: How do I discover topics before searching with Uniphore Conversation AI and Vercel AI SDK?

Use the listtopics tool. This shows all tracked keywords across your organization, giving you a controlled list of terms to pass into searchmeetings.

See meeting insights live: Uniphore Conversation AI for 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 Uniphore Conversation AI MCP to Vercel AI SDK

Create your Vinkius account to connect Uniphore Conversation AI 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 Uniphore Conversation AI with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Streaming Meeting Data with the MCP Server

The `get_transcript` tool delivers the full text of any recorded call, streaming it directly into your Next.js or React UI. Users see the dialogue appear in real-time—no waiting for a loading spinner. This immediate feedback loop makes building complex chat interfaces simple. Your agent can stream multiple results from Uniphore Conversation AI right as they happen.

Listing and Searching Meetings via Vercel AI SDK

Need to find a specific conversation? Use `list_meetings` first, then use `search_meetings` by keyword or topic. The results stream quickly, letting your client populate the search list instantly. This is perfect for creating dashboards where users need immediate access to historical data without page reloads.

Getting Action Items in Real-Time

The `get_action_items` tool extracts specific next steps from a meeting and streams them back. You'll get clear, actionable bullet points that appear on the screen as soon as they are processed. This means your user doesn't wait for an API call to finish; they watch the items populate live, improving perceived performance.

Setup guide

Set up Uniphore Conversation AI 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 Uniphore Conversation AI 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 Uniphore Conversation AI 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 Uniphore. 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 Uniphore Conversation AI 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 Uniphore Conversation AI MCP in Vercel AI SDK

First, use `list_meetings` to get all available IDs. Then, call `search_meetings`, passing the keyword or topic you need. The results populate in your client immediately.

Yeah, it does. You can use `get_meeting_analytics` and stream the insights directly into your UI using the Vercel AI SDK. It keeps the user engaged because the data appears live.

You can get summaries for any meeting ID retrieved using `get_meeting`. The summary is streamed, so your user sees the text appear piece by piece in the client.

Use the `list_topics` tool. This shows all tracked keywords across your organization, giving you a controlled list of terms to pass into `search_meetings`.

The server handles meeting transcripts and conversation analytics data. When building with the Vercel AI SDK, you're dealing with streaming versions of these sensitive records.

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