How to Use the MiiTel MCP in Vercel AI SDK

Stream real-time MiiTel call sentiment and coaching metrics directly into your AI SDK frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MiiTel MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Call Analytics in React

Feed your UI live call data by piping `list_calls` directly into your stream. You get the quality scores and sentiment markers as they happen. Your users see the analysis populate the screen without waiting for a backend refresh. It turns raw audio logs into a visual feedback loop for your sales reps.

Targeted Meeting Insights

Call `get_meeting_details` to grab the specifics on any recorded session. You can now build custom dashboards that highlight exactly where a conversation went off the rails. Connecting this to your AI SDK lets you show managers the precise moment a lead dropped off. It removes the guesswork from your sales coaching workflow.

Unified Contact Directory

Pull your CRM data into the view using `list_synced_contacts`. Your frontend now has instant access to the names and numbers mapped to every MiiTel interaction. This makes it simple to tag specific users or filter call logs by client. Everything stays in sync with your production data through your existing edge functions.

Setup guide

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

You install the MCP client package and point it to your server endpoint. Once connected, your tools like `list_calls` become available as standard functions in your stream logic.

Yes. Since you are using streaming responses, the tool results flow to your UI components immediately. Your users see the sentiment shifts the moment the analysis finishes.

It does. The server communicates over standard HTTP, making it compatible with your edge runtime environment. You just manage the connection lifecycle in your client code.

You catch them like any other promise rejection in your TypeScript code. If a tool fails, you can trigger a fallback or show a specific alert in your interface.

The server only touches call metadata and transcript IDs that you explicitly request. Your AI client acts as a secure pipe, keeping the underlying audio files on MiiTel 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