How to Use the Clickatell MCP in Vercel AI SDK

Q: How do I send SMS with Clickatell and the Vercel AI SDK?

You pass the dispatchsmsmessage or dispatchbulksms tools from this server to the AI SDK's generateText function. The SDK handles calling the tool and streaming the result back to your UI components.

Q: Can I track message delivery using Clickatell with the Vercel AI SDK?

Yes, that's one of its main strengths. Use the getdeliverystatus tool. Because the Vercel AI SDK streams results, you can build a UI that updates the status in real-time as the data arrives from the carrier.

Q: What's the best way to manage inbound rules for Clickatell in my Vercel AI SDK app?

Expose the upsertinboundrule and wipeinboundrule tools to your AI agent. This lets your application create and destroy webhook routing on the fly, directly from your frontend logic.

Q: How does this MCP Server handle bulk messaging?

It uses the dispatchbulksms tool, which is optimized for Clickatell's pipeline. It takes an array of messages and sends them efficiently, avoiding the lag you'd get from calling a single-send API in a loop.

Build UIs that send SMS and show live delivery status, all powered by Clickatell and 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 Clickatell MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send SMS Directly From Your UI

Connect the Vercel AI SDK to this server and your React or Next.js app can fire off text messages. The `dispatch_sms_message` tool sends a single SMS over Clickatell's network. For larger sends, `dispatch_bulk_sms` pushes arrays of messages without bogging down your app. You're not just sending messages into the void. The tool results stream back, so your UI can confirm the message was sent and update instantly. No more guessing if the API call worked.

Stream Live Status via the MCP Server

This is the cool part. Your user-facing dashboard can show the exact status of a sent message. The `get_delivery_status` tool pulls the final carrier status directly from Clickatell's backend. Because the AI SDK streams tool results, you can build components that update from "sent" to "delivered" live, right in front of the user. It's a much better experience than making them refresh a page. You can also check your remaining funds with `get_account_balance`.

Manage Inbound Rules from the Frontend

Let your users manage how they receive inbound messages without leaving your app. The `upsert_inbound_rule` tool creates new rules, pointing incoming SMS to a webhook you define. This means you can build a settings page where an AI agent handles the configuration. Need to see what's already set up or tear something down? `list_inbound_rules` gives you a full list of your current configurations, and `wipe_inbound_rule` deletes a rule by its ID. It gives your UI full control over the inbound logic.

Setup guide

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

You pass the `dispatch_sms_message` or `dispatch_bulk_sms` tools from this server to the AI SDK's `generateText` function. The SDK handles calling the tool and streaming the result back to your UI components.

Yes, that's one of its main strengths. Use the `get_delivery_status` tool. Because the Vercel AI SDK streams results, you can build a UI that updates the status in real-time as the data arrives from the carrier.

Expose the `upsert_inbound_rule` and `wipe_inbound_rule` tools to your AI agent. This lets your application create and destroy webhook routing on the fly, directly from your frontend logic.

It uses the `dispatch_bulk_sms` tool, which is optimized for Clickatell's pipeline. It takes an array of messages and sends them efficiently, avoiding the lag you'd get from calling a single-send API in a loop.

Your Vercel AI SDK app talks to the MCP Server, which handles the auth with Clickatell. The server itself is ephemeral and runs in a zero-trust sandbox. It only holds message data and phone numbers (MSISDNs) in memory for the duration of the API call.

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