How to Use the Bandwidth MCP in Mastra AI

Q: How do I configure the Bandwidth MCP Server in Mastra AI?

Instantiate a new MCPClient and pass your Vinkius endpoint URL into the servers object. Mastra automatically detects whether to use Streamable HTTP or SSE for the transport layer.

Q: Can Mastra AI retry failed Bandwidth SMS messages?

The framework handles exponential backoff natively. If a sendsms call fails due to a rate limit, the workflow engine waits and tries again automatically.

Q: Does Mastra AI require approval to send Bandwidth MMS?

You can configure requireToolApproval for the sendmms tool. This pauses the workflow until a human reviews the media payload and authorizes the dispatch.

Q: What happens if my toll-free verification fails?

Conditional branching catches the failure from gettollfree. You can route the workflow to open a support ticket instead of attempting to send traffic over an unverified number.

Build resilient telecom workflows that automatically retry failed Bandwidth texts using Mastra AI.

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 Mastra AI

Create your Vinkius account to connect Bandwidth to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate 10DLC Campaign Audits

`list_campaigns` grabs all registered carrier compliance records for your messaging traffic. Mastra AI can route this data through conditional branches, checking if any campaigns are nearing expiration or missing approval. If an issue surfaces, the workflow immediately alerts an administrator. Deep dives happen with `get_campaign` when a specific ID needs inspection. You map this tool into a background job that runs daily. The agent verifies the throughput limits and automatically adjusts your outbound sending rates based on the returned data.

Resilient SMS Dispatch Workflows

`send_sms` pushes text messages through the carrier network. Because Mastra AI handles exponential backoff natively, temporary API timeouts or network blips will not kill your outbound alerts. The system automatically tries again if the initial request drops. Sending richer content uses `send_mms` to attach images or audio. If a specific media file fails to attach, your workflow can catch the error, swap to a fallback text-only payload, and guarantee the user still gets the notification.

Connect Bandwidth MCP to Mastra

`list_applications` pulls your active messaging apps configured on the telecom side. Your workflow engine uses this to map incoming numbers to the correct internal routing logic. Setting up the connection takes one command by passing the Vinkius URL to the `MCPClient` constructor. Checking connection stability relies on `get_health` to ping the API before starting a massive text blast. Spreading `mcpClient.listTools()` directly into your Agent tools array exposes the entire suite instantly. You get full access to the telecom stack with zero custom integration code.

Setup guide

Set up Bandwidth MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Bandwidth tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "bandwidth-mcp-client",
  servers: {
    "bandwidth-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Bandwidth Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Bandwidth tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Bandwidth transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate a new `MCPClient` and pass your Vinkius endpoint URL into the servers object. Mastra automatically detects whether to use Streamable HTTP or SSE for the transport layer.

The framework handles exponential backoff natively. If a `send_sms` call fails due to a rate limit, the workflow engine waits and tries again automatically.

You can configure `requireToolApproval` for the `send_mms` tool. This pauses the workflow until a human reviews the media payload and authorizes the dispatch.

Conditional branching catches the failure from `get_toll_free`. You can route the workflow to open a support ticket instead of attempting to send traffic over an unverified number.

Every API request runs inside an isolated, short-lived sandbox. Your campaign IDs and toll-free verification details are never stored at rest, as the execution environment is completely destroyed once the Mastra workflow completes the step.

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