How to Use the Codemagic MCP in Mastra AI

Q: How do I set up automatic retries for failed Codemagic builds in Mastra AI?

You wrap the startbuild tool in a Mastra AI workflow block. If the Codemagic API returns a rate limit or transient error, Mastra's built-in retry mechanism executes the call again based on your backoff settings.

Q: How do I pass build parameters from Mastra AI to Codemagic workflows?

You map your agent's output directly to the arguments of startbuild. The Mastra AI framework handles the schema validation, ensuring the branch and environment variables match what the CI pipeline expects.

Q: How does the agent fetch specific artifacts from a completed build over MCP?

The agent uses getartifact to retrieve the authenticated download URL of the IPA or APK file. It can then pass this file path to subsequent tools in your automation chain.

Automate complex mobile CI/CD pipelines with conditional branching and automatic retries using Mastra AI and this Codemagic 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 Mastra AI

Create your Vinkius account to connect Codemagic 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 Codemagic with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate resilient multi-step mobile builds

The `start_build` tool kicks off your mobile compilations within a Mastra AI workflow. If a build fails due to a temporary network glitch, Mastra's built-in retry engine automatically triggers the run again without human intervention. You can write conditional logic that checks the build status. If the compile succeeds, the workflow moves to the next step; if it fails, the agent handles the error cleanup.

Auto-manage build variables during failures

The `add_variables_to_group` tool updates build configurations dynamically inside your Mastra AI agent loops. When a deployment fails due to expired credentials, your agent can catch the error, grab updated keys from your vault, and inject them into the Codemagic variable group. This self-healing pipeline keeps your release process moving. The agent performs these updates securely within its execution context, minimizing manual intervention during midnight release cycles.

Automate QA distribution loops

The `create_public_artifact_url` tool generates public testing links that your Mastra AI workflows route to your distribution channels. As soon as the build finishes, the workflow fetches the artifact metadata using `get_artifact` and generates the sharing link. If the download generation fails, Mastra's workflow engine retries the call with exponential backoff. This ensures your QA team always receives their testing builds even during peak API traffic.

Setup guide

Set up Codemagic 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 Codemagic 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: "codemagic-mcp-client",
  servers: {
    "codemagic-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Codemagic 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 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 Mastra AI

You wrap the `start_build` tool in a Mastra AI workflow block. If the Codemagic API returns a rate limit or transient error, Mastra's built-in retry mechanism executes the call again based on your backoff settings.

Yes, you can design a Mastra AI agent that monitors build metrics and uses `cancel_build` to stop stuck runs. This keeps your mobile pipeline efficient and prevents budget overruns.

You map your agent's output directly to the arguments of `start_build`. The Mastra AI framework handles the schema validation, ensuring the branch and environment variables match what the CI pipeline expects.

The agent uses `get_artifact` to retrieve the authenticated download URL of the IPA or APK file. It can then pass this file path to subsequent tools in your automation chain.

This MCP Server processes your environment variable updates in memory inside an ephemeral V8 sandbox. Your sensitive mobile signing keys and API credentials never persist on disk, ensuring strict compliance with enterprise security policies.

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