How to Use the Bandwidth MCP in Cursor

Q: Can Cursor generate a script to send bulk SMS with Bandwidth?

Yes. Ask the agent to use the sendsms tool as a starting point. For example: "Write a Node.js script that reads a CSV of numbers and sends a message to each one using the Bandwidth sendsms tool."

Q: Can I use Bandwidth and Cursor to check the status of my campaigns?

Absolutely. Just tell the agent, "Use getcampaign with ID '12345' and show me the details." It will call the tool and paste the live data right into the chat or your code.

Generate code that uses the live Bandwidth API. Pull real message logs and campaign data directly into your editor with Cursor.

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 Cursor

Create your Vinkius account to connect Bandwidth to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Write API Clients with Real Data

Stop guessing at API response structures. Tell Cursor's agent, "get the last 5 messages using `list_messages` and write a Python function to parse them." It calls the tool, gets a real response, and generates code that actually works. This kills the back-and-forth of testing against a live API. This works for any tool your MCP server exposes. Ask Cursor to use `get_campaign` to fetch a campaign object, then tell it to generate the code that modifies that object's properties. You're coding against real structures, not documentation.

Test Messaging Code in Your Editor with Cursor

You're writing a function that sends an alert. Highlight the code and tell the agent, "run this, but use the `send_sms` tool to send a test message to my number." You get immediate feedback without deploying or running a separate script. You can even send an MMS with `send_mms` to test media handling. This closes the loop between writing and testing. You can also build quick diagnostic tools. Ask Cursor to use `get_health` to check the API status and `list_toll_free` to verify numbers, then write a script that combines them.

Manage Bandwidth Resources via an MCP Server

This isn't just about writing code. You can manage your account directly from the editor's chat. Need to clean up old test files? Tell the agent, "list all media files with `list_media`, then delete the ones older than 30 days using `delete_media`." It's like having a CLI for your Bandwidth account, but with natural language. You can use `list_campaigns` and `list_applications` to get an overview of your setup without ever leaving your code. It keeps you in the flow.

Setup guide

Set up Bandwidth MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Bandwidth MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Bandwidth transactions." If the MCP tools are loaded correctly, Cursor will call the Bandwidth tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "bandwidth-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

Yes. Ask the agent to use the `send_sms` tool as a starting point. For example: "Write a Node.js script that reads a CSV of numbers and sends a message to each one using the Bandwidth `send_sms` tool."

The Vinkius MCP server holds the connection to Bandwidth. Your editor's agent just makes a secure call to the server's endpoint. Your API keys are never exposed in your local project files.

Absolutely. Just tell the agent, "Use `get_campaign` with ID '12345' and show me the details." It will call the tool and paste the live data right into the chat or your code.

It's about speed and context. The agent doesn't just fetch data; it understands your code. It can inject the live API response from `list_messages` directly into a variable or generate a new function based on the `get_campaign` data structure.

Only the data needed for a specific tool call is processed. If you use `send_sms`, the phone number and message content pass through. The Vinkius MCP server is ephemeral and doesn't store your telecom data after the operation is done.

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