How to Use the Codemagic MCP in CrewAI

Q: How do CrewAI agents share Codemagic artifact URLs with each other?

The agent that executes getartifact passes the retrieved URL into the CrewAI shared memory. This allows downstream agents, like a Slack notification agent, to access and share the link.

Run autonomous multi-agent mobile release crews that trigger, monitor, and distribute Codemagic builds over MCP with CrewAI.

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 CrewAI

Create your Vinkius account to connect Codemagic to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent mobile deployments

The `start_build` tool allows your CrewAI release manager agent to initiate mobile compilations while other specialized agents monitor the progress. A dedicated QA agent can wait for the build to finish, ready to process the output files. This team-based approach mimics a human release squad. The coordinator agent triggers the build on Codemagic, and the QA agent takes over the moment the artifact becomes available.

Automate variable management across agent roles

The `add_variables_to_group` tool lets your CrewAI security agent update environment configurations without exposing raw keys to other agents in the crew. When a new release requires updated API endpoints, the security agent writes them directly to the Codemagic group. By segregating roles, you ensure that only the authorized security agent handles sensitive credentials. Other agents in your CrewAI setup continue their work without ever seeing the raw variables.

Deliver artifacts to QA agents autonomously

The `create_public_artifact_url` tool enables your distribution agent to generate public URLs for test builds and hand them off to external testing teams. The agent calls `get_artifact` to locate the compiled binary, then creates the public link instantly. This removes human bottlenecks from the QA loop. Your CrewAI agents manage the entire handoff, from checking build completion to posting the download link in your team's chat channels.

Setup guide

Set up Codemagic MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Codemagic tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Codemagic Analyst",
    goal="Access and analyze Codemagic data via MCP.",
    backstory="Expert analyst with direct Codemagic access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Codemagic transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Codemagic Analyst",
        goal="Access and analyze Codemagic data via MCP.",
        backstory="Expert analyst with direct Codemagic access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Codemagic transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You define a specialized Release Agent in CrewAI and equip it with the `start_build` tool. This agent focuses solely on triggering and managing the Codemagic build lifecycle while other agents handle testing.

Yes, a supervisor agent in your CrewAI setup can monitor build logs and call `cancel_build` if it detects a compilation error. This prevents your team from wasting build credits on broken code.

The agent that executes `get_artifact` passes the retrieved URL into the CrewAI shared memory. This allows downstream agents, like a Slack notification agent, to access and share the link.

Yes, you can chain these tools sequentially. For example, Agent A updates variables, Agent B starts the build, and Agent C retrieves the finished artifact in a structured pipeline.

Your API keys are never stored by the MCP Server or the Vinkius platform. All authentication tokens exist strictly in memory within an ephemeral V8 sandbox, protecting your mobile application credentials from exposure.

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