How to Use the JustCall MCP in Vercel AI SDK

Q: How do I connect the JustCall MCP Server to my Vercel AI SDK project?

Install the @ai-sdk/mcp package and initialize the client using createMCPClient with your Vinkius HTTP transport URL. Pass the tools directly into generateText or streamText to let your agent call them. Remember to call close() on the client when the execution finishes to prevent memory leaks.

Q: Can I stream call recordings directly to the frontend using JustCall and Vercel AI SDK?

Yes, the listrecordings tool retrieves the audio file links and metadata. Your application can immediately stream these URLs into a native HTML5 audio player on your frontend. This lets users listen to calls directly in their browser without manual downloads.

Q: What is the fastest way to sync contacts between JustCall and Vercel AI SDK?

Use listcontacts to pull contact records and stream them directly into your UI components. The SDK handles the data stream chunk by chunk, so your users see names and numbers populate instantly. This removes the need for loading spinners during high-volume lookups.

Build live communication dashboards that stream real-time JustCall phone and SMS data directly into Next.js 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 JustCall MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Call Tracking in Next.js

The `list_calls` tool pulls your live call history, direction, and duration directly into your UI. Your agent processes this raw data and updates your interface on the fly without making the user wait for a page reload. You get immediate visibility into active JustCall support queues. By combining this with `get_call`, your application displays deep-dive call details, participants, and agent notes the second a call wraps up.

Real-time SMS Feeds via Vercel AI SDK MCP Server

The `list_messages` tool fetches incoming and outgoing text interactions alongside their delivery status. Since this MCP Server runs on Vercel's edge network, your AI client renders text conversations inside your chat component with zero latency. Users see messages populate on their screens in real-time. You don't have to build complex polling mechanisms because the SDK streams the tool outputs directly into your React or Svelte state.

Instant Contact Verification

The `list_contacts` tool retrieves names, phone numbers, and unique identifiers from your database. When a call comes in, your application immediately matches the number to an existing profile using `get_contact` to show agent notes. This prevents agents from flying blind during critical customer interactions. It fetches phone numbers and emails instantly, letting your team vet callers before they even pick up the line.

Setup guide

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

Install the `@ai-sdk/mcp` package and initialize the client using `createMCPClient` with your Vinkius HTTP transport URL. Pass the tools directly into `generateText` or `streamText` to let your agent call them. Remember to call `close()` on the client when the execution finishes to prevent memory leaks.

Yes, the `list_recordings` tool retrieves the audio file links and metadata. Your application can immediately stream these URLs into a native HTML5 audio player on your frontend. This lets users listen to calls directly in their browser without manual downloads.

The Vinkius hosted server handles the heavy lifting, allowing your edge functions to remain lightweight. You only need to make a fast HTTP fetch to the server endpoint. This keeps your Next.js edge runtimes well under the execution limit.

Use `list_contacts` to pull contact records and stream them directly into your UI components. The SDK handles the data stream chunk by chunk, so your users see names and numbers populate instantly. This removes the need for loading spinners during high-volume lookups.

Your communication logs, SMS texts, and contact details stay completely secure. Vinkius runs this server inside an isolated V8 sandbox, meaning your call records and customer phone numbers are never stored or used for model training. All data transfers use encrypted transit tunnels directly to your client.

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