How to Use the Courier MCP in Vercel AI SDK

Q: How do I use the Courier MCP server with the Vercel AI SDK to check message status?

Connect the server, then prompt your agent to use listmessages or getmessagehistory. The Vercel AI SDK is built for this; it will stream the delivery logs directly into your UI components in real time.

Q: Can I send notifications using Courier and the Vercel AI SDK?

Yes. Your agent can call the sendnotification tool. It uses your existing Courier templates and recipient profiles, so there's nothing new to configure.

Q: What's the best way to handle Courier audiences in a Vercel AI SDK app?

Have your agent call listaudiences to fetch the available segments. You can then display these in your UI and pass the selected audience ID to the sendnotification tool when a user wants to send a broadcast.

Build UIs that show Courier delivery status in real time. Your Vercel AI SDK app now talks directly to your notification service.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Courier MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor Notifications Live in Your UI

Stop showing your users a loading spinner. With the Vercel AI SDK, you can ask your agent for a message's status and watch the data stream directly into your React components. It's perfect for building internal dashboards where support staff needs answers now. Your agent gets the job done using `list_messages` for an overview or `get_message_history` to pull detailed delivery logs for a single send. The AI SDK turns that data into a live-updating view, so your user sees the information as it arrives. This is how you build apps that feel instant.

Interactive User and Brand Management

Your AI-powered frontend can now manage Courier settings. Let your agent pull a user's contact information and notification preferences with `get_user_profile` before sending them a message. You can even pull a list of configured brands using `list_brands` to make sure your UI matches the notification. This isn't just for display. Let your admin users ask the AI to check on a user's details without having to switch tabs to the Courier dashboard. An agent can use `list_users` to find someone in the workspace and then check their profile. This is a perfect use case for an MCP Server connected to your frontend tools.

Trigger Notifications with the AI SDK

Give your agent the authority to send messages. The `send_notification` tool lets your AI client fire off any message from your existing Courier templates. Your app just tells the agent what to send and who to send it to. Before sending, your agent can do its homework. It can call `list_templates` to find the right template ID or use `list_audiences` to see available recipient groups. Your UI can confirm the send immediately. It's a much cleaner experience, and it's all possible because this MCP server handles the API connection.

Setup guide

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

Connect the server, then prompt your agent to use `list_messages` or `get_message_history`. The Vercel AI SDK is built for this; it will stream the delivery logs directly into your UI components in real time.

Yes. Your agent can call the `send_notification` tool. It uses your existing Courier templates and recipient profiles, so there's nothing new to configure.

Have your agent call `list_audiences` to fetch the available segments. You can then display these in your UI and pass the selected audience ID to the `send_notification` tool when a user wants to send a broadcast.

It works with any template already in your Courier workspace. Your agent can call `list_templates` to get a fresh list of available template IDs and names at any time.

This MCP server only accesses Courier data like delivery logs, recipient profiles, and template metadata. All requests are proxied through Vinkius's sandboxed environment, and your endpoint token is the only credential needed. Your app's code never touches raw API keys.

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