How to Use the Codemagic MCP in Pydantic AI

Q: Can Pydantic AI stop a Codemagic build?

You can use cancelbuild at any time. Because it's part of the MCP toolset, it follows your strict validation rules to ensure the build ID is accurate.

Q: How do I share Codemagic artifacts with Pydantic AI?

Call createpublicartifacturl to get a link. Pydantic AI validates the response format, ensuring you can safely share the URL with your team.

Build type-safe mobile CI/CD pipelines with Pydantic AI and Codemagic.

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 Pydantic AI

Create your Vinkius account to connect Codemagic to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe build execution with Pydantic AI

Every call to `start_build` is validated against your schema. If the agent provides an invalid parameter, Pydantic AI rejects it before the request hits Codemagic. This ensures your pipeline starts with valid configuration settings. It prevents common runtime errors in your build orchestration.

Strict artifact management for Pydantic AI

The `get_artifact` tool returns data that matches your Pydantic models. You get a clear, structured view of your build binary paths and status. If the data structure doesn't match your expectations, the agent fails immediately. You never have to deal with silent data corruption.

Validated environment updates in Pydantic AI

Use `add_variables_to_group` to manage your environment variables with full type safety. Your agent updates your Codemagic groups only if the payload is correct. This creates a reliable link between your code and your CI/CD settings. It removes the guesswork from variable injection.

Setup guide

Set up Codemagic MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "codemagic-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Codemagic tools.",
)

result = await agent.run("List recent Codemagic transactions")
print(result.output)

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 Pydantic AI

Add the MCP toolset to your agent instance. Pydantic AI will automatically validate all tool responses against your defined models at runtime.

You can use `cancel_build` at any time. Because it's part of the MCP toolset, it follows your strict validation rules to ensure the build ID is accurate.

It provides runtime validation for all API interactions. If Codemagic returns unexpected data, your agent catches it instantly, ensuring your pipeline logic remains stable.

Call `create_public_artifact_url` to get a link. Pydantic AI validates the response format, ensuring you can safely share the URL with your team.

All data exchanged is strictly typed and validated within your local agent environment. No sensitive data is leaked because every interaction is constrained by your schema.

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