Codemagic MCP Server
A lightweight, community-maintained Model Context Protocol (MCP) server that provides seamless access to Codemagic CI/CD APIs. Built for agents, AI-native workflows, and for use of MCP-compatible clients.
🌐 How can you use this
You: What applications do I have on Codemagic?
Assistant: calls get_all_applications() and displays the list.
You: Start a new build for my Flutter app
Assistant: calls start_build() with appropriate parameters
You: Can you get the artifacts from my last build?
Assistant: calls get_builds() to find the latest build and then get_artifact() to download the files
You: Show me the cache usage for my app
Assistant: calls get_app_caches() and displays storage information
🌐 Getting started
1. Clone this repository
git clone https://github.com/stefanoamorelli/codemagic-mcp.git
cd codemagic-mcp
2. Set up your API key
Follow the official documentation.
3. Install the MCP server in your client
For example, for Claude Desktop:
{
"mcpServers": {
"Codemagic MCP Server": {
"command": "uv",
"args": [
"run",
"--with",
"mcp[cli]",
"--with",
"requests",
"mcp",
"run",
"<global_path_to_the_cloned_repo>/codemagic_mcp/server.py"
],
"env": {
"PYTHONPATH": "<global_path_to_the_cloned_repo>/",
"CODEMAGIC_API_KEY": "your-api-key-here"
}
},
}
📈 What this server can do
Interact with Codemagic CI/CD using natural language.
| API Category | Tools |
|---|---|
| Applications API | get_all_applications, get_application, add_application, add_application_private |
| Artifacts API | get_artifact, create_public_artifact_url |
| Builds API | start_build, get_builds, get_build_status, cancel_build |
| Caches API | get_app_caches, delete_all_app_caches, delete_app_cache |
| Teams API | invite_team_member, delete_team_member |
🛠️ Development
Run the server locally for testing:
mcp dev codemagic_mcp/server.py
📚 References
📜 License
MIT License © 2025 Stefano Amorelli
Recommend MCP Servers 💡
@aashari/mcp-server-aws-sso
Node.js/TypeScript MCP server for AWS Single Sign-On (SSO). Enables AI systems (LLMs) with tools to initiate SSO login (device auth flow), list accounts/roles, and securely execute AWS CLI commands using temporary credentials. Streamlines AI interaction with AWS resources.
k8s-mcp-server
K8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kubernetes CLI tools including kubectl, helm, istioctl, and argocd, allowing AI systems to assist with cluster management, troubleshooting, and deployments
ej-mcp-server-gdrive
Integrates with Google Drive to allow listing, reading, and searching over files via MCP
mcp-server-opendal
Model Context Protocol Server for Apache OpenDAL™
datadog-mcp-server
An MCP server that integrates with the official Datadog API, providing tools to access monitoring data, dashboards, metrics, events, logs, and incidents.
Intruder
An MCP server by Intruder that integrates with Claude AI to streamline exposure management by enabling users to execute tasks and gather insights from the Intruder platform.