How to Use the Bandwidth MCP in Vercel AI SDK

Q: How do I connect the Bandwidth MCP Server to Vercel AI SDK?

Install the @ai-sdk/mcp package in your project. Call createMCPClient with your Vinkius HTTP transport URL. Pass the resulting tool array into your streamText function.

Q: How do I close the connection after sending a message?

Always invoke mcpClient.close() when your text generation finishes. This prevents memory leaks and orphaned connections in your serverless functions.

Stream live SMS dispatch and telecom data straight to your React frontend using the Bandwidth MCP Server and 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 Bandwidth MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream SMS Logs to Vercel AI SDK

`list_messages` retrieves sent and received text logs directly from your telecom account. Your Vercel AI SDK application pipes these records straight into a Next.js dashboard as they arrive. Users watch their message history populate instantly without waiting for bulk API queries to finish. Sending outbound texts works the same way via `send_sms`. The agent triggers the dispatch tool, and the result streams back to the UI component confirming delivery. You build interactive telecom interfaces where the AI handles the routing while the user sees the confirmation live.

Manage MMS Media Assets Live

`list_media` fetches all uploaded files currently sitting in your storage buckets. Connecting this MCP Server means your frontend can display available images or audio clips before a user decides to attach them to an outbound blast. When someone needs to push an image out, `send_mms` attaches the specific payload and fires it off. Cleaning up old files happens through `delete_media`, keeping your storage costs down while the UI reflects the deletion immediately.

Track 10DLC Campaign Health

`list_campaigns` pulls your active 10DLC messaging configurations to ensure carrier compliance. Your agent checks these records before allowing a user to send high-volume traffic. This prevents accidental blocking from major cell networks. Drilling down into specific details requires `get_campaign`. The AI reads the exact throughput limits and use cases approved for that number. `get_toll_free` also verifies toll-free number statuses, keeping your entire messaging operation above board.

Setup guide

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

Install the `@ai-sdk/mcp` package in your project. Call `createMCPClient` with your Vinkius HTTP transport URL. Pass the resulting tool array into your `streamText` function.

Yes, the frontend receives tool execution results in real-time. When the agent fires `send_sms`, the confirmation payload streams back to the user interface instantly.

The HTTP transport layer works perfectly within Edge environments. You just need to ensure the Vinkius endpoint token is available in your environment variables.

Always invoke `mcpClient.close()` when your text generation finishes. This prevents memory leaks and orphaned connections in your serverless functions.

Vinkius executes every tool call inside an ephemeral V8 Isolate Sandbox. Your message contents and media payloads pass through a zero-trust environment that spins down immediately after the request completes. No data persists on the platform.

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