How to Use the Nimbata MCP in Vercel AI SDK

Q: How do I initialize Nimbata with the Vercel AI SDK?

Run npm install @ai-sdk/mcp. Use createMCPClient with an HTTP transport pointing to your endpoint. Pass the resulting tools directly into your generateText or streamText calls.

Q: Can the Vercel AI SDK stream Nimbata call recordings?

Yes. The AI triggers getcallrecording to fetch the audio file reference. Your frontend can then render an HTML5 audio player for the user to listen immediately.

Q: How does the Vercel AI SDK handle Nimbata campaign creation?

A user asks to track a new Facebook ad. The agent calls createsource to set up the attribution, then returns the allocated phone numbers directly to the chat interface.

Stream live call tracking data and attribution reports straight into your React frontend 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 Nimbata MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Call Data to the UI

The `list_calls` and `search_calls` tools pull active phone call sessions directly from Nimbata. Your Vercel AI SDK agent streams this data into a Next.js dashboard as the calls happen, skipping the traditional loading spinners. Users see caller IDs and durations populate instantly. You just pass the MCP client tools to `streamText`, and the AI renders the incoming call log on the screen before the caller even hangs up.

Vercel AI SDK MCP Server Integration

The `get_source_report` tool calculates exactly which marketing campaigns drove phone traffic. Your agent fetches the attribution numbers and streams a complete breakdown of ad spend versus call volume into your application. You do not have to write custom aggregation logic. The AI calls `get_call_report` to tally the metrics, then formats the output into a live chart component for your marketing team.

Provision Tracking Numbers on the Fly

The `create_source` tool generates new dynamic tracking pools for fresh marketing campaigns. A user types a campaign name into your app, and the AI provisions the numbers instantly in the background. After creation, the agent uses `list_numbers` to confirm the assignment. It then updates the UI to show the new phone numbers ready for deployment on landing pages.

Setup guide

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

Run `npm install @ai-sdk/mcp`. Use `createMCPClient` with an HTTP transport pointing to your endpoint. Pass the resulting tools directly into your `generateText` or `streamText` calls.

Yes. The AI triggers `get_call_recording` to fetch the audio file reference. Your frontend can then render an HTML5 audio player for the user to listen immediately.

The MCP standard lets the AI decide which tool to call based on the user's prompt. You avoid writing rigid API wrappers and let the model handle the parameter mapping dynamically.

A user asks to track a new Facebook ad. The agent calls `create_source` to set up the attribution, then returns the allocated phone numbers directly to the chat interface.

The system processes raw audio files and phone numbers. Vinkius runs this MCP Server in a V8 Isolate Sandbox that destroys the execution environment immediately after the request finishes, leaving zero residual data behind.

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