How to Use the Codemagic MCP in Vercel AI SDK

Q: How do I stream Codemagic build logs in real-time using the Vercel AI SDK?

You hook the startbuild tool into your streamText function to trigger the compilation. The Vercel AI SDK then streams the initial build payload directly to your React components, letting you render status updates without loading spinners.

Q: How does the Vercel AI SDK handle sensitive Codemagic environment variables?

The SDK passes encrypted payloads to the addvariablestogroup tool. This ensures your mobile signing keys and API secrets move securely from your UI to Codemagic without exposure in client-side logs.

Q: What happens if a Codemagic build hangs during an MCP session?

Your agent can call cancelbuild to stop the run immediately. This prevents unnecessary credit consumption and keeps your queue clear for other team members.

Run Codemagic builds and stream live deployment statuses into Next.js using Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Codemagic MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger mobile builds with live UI streaming

The `start_build` tool lets your Vercel AI SDK app kick off iOS or Android builds on Codemagic without making users wait for a full page reload. Because the SDK supports streamable tool calls, you can render the build status inline as soon as the API responds. Developers get a direct feedback loop where the prompt starts the compilation and the UI updates in real-time. This setup runs on Edge Functions, keeping your Next.js serverless architecture lightweight while managing heavy mobile CI pipelines.

Inject build variables directly from web forms

The `add_variables_to_group` tool updates your Codemagic environment variables directly through your Vercel AI SDK chat interface. Instead of digging through the CI dashboard, your team types new API keys or version numbers into the chat, and the agent updates the group instantly. This eliminates the need to manually copy-paste sensitive credentials across multiple browser tabs. Your React components display immediate confirmation of the variable updates, keeping your mobile deployment configs secure and synchronized.

Generate instant public download links

The `create_public_artifact_url` tool generates public sharing links for your compiled IPA or APK files, which your Vercel AI SDK interface displays as clickable download buttons. Your QA testers don't need to log into the CI portal; they just click the streamed link in their chat window. If you need to fetch specific build metadata first, the `get_artifact` tool retrieves the authenticated download path. This combination lets you build custom, internal release dashboards that stream raw build outputs directly to your team's browsers.

Setup guide

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

You hook the `start_build` tool into your `streamText` function to trigger the compilation. The Vercel AI SDK then streams the initial build payload directly to your React components, letting you render status updates without loading spinners.

Yes, this MCP Server works in edge environments. You initialize the MCP client inside your Next.js Route Handler and pass the `start_build` tool to `streamText` for fast, serverless execution.

The SDK passes encrypted payloads to the `add_variables_to_group` tool. This ensures your mobile signing keys and API secrets move securely from your UI to Codemagic without exposure in client-side logs.

Your agent can call `cancel_build` to stop the run immediately. This prevents unnecessary credit consumption and keeps your queue clear for other team members.

Vinkius runs this MCP Server in an isolated V8 sandbox, meaning your API tokens and build artifacts never touch persistent storage. Only the ephemeral session has access to the keys required for triggering builds, and all data wipes instantly when the call ends.

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