{
  "markdown": "# Cloud Composer Managed MCP Extension\n\n> **Preview:** This product is subject to the \"Pre-GA Offerings Terms\" in the\n> General Service Terms section of the\n> [Service Specific Terms](https://docs.cloud.google.com/terms/service-terms#1).\n> Pre-GA products and features are available \"as is\" and might have limited\n> support. For more information, see the\n> [launch stage descriptions](https://cloud.google.com/products#product-launch-stages).\n\nThe Cloud Composer managed MCP extension allows users to manage their Managed\nAirflow environments and get details about executed DAG runs and Airflow tasks.\n\n## Why use the Cloud Composer managed MCP server?\n\nGoogle and Google Cloud\n[managed MCP servers](https://docs.cloud.google.com/mcp/overview) can be used in\nyour AI applications with enterprise-ready governance, security, and access\ncontrol.\n\n## Before you begin\n\n1.  In the Google Cloud console, on the\n    [project selector page](https://console.cloud.google.com/projectselector2/home/dashboard),\n    select or create a Google Cloud project. > **Note**: If you don't plan to\n    keep the resources that you create in this > procedure, create a project\n    instead of selecting an existing project. > After you finish these steps,\n    you can delete the project, removing all > resources associated with the\n    project.\n2.  Get your administrator to grant you the\n    [MCP Tool User role](https://docs.cloud.google.com/iam/docs/roles-permissions/mcp#mcp.toolUser)\n    (`roles/mcp.toolUser`) on the Google Cloud project. If you created a new\n    project, then you already have the required permissions.\n3.  Ensure your administrator has enabled the\n    [Cloud Composer API](https://console.cloud.google.com/marketplace/product/google/composer.googleapis.com)\n    on the Google Cloud project.\n\n## Configure authentication\n\nThis extension uses Google Application Default Credentials (ADC) to perform\nauthentication. To login with ADC, run the following command in your terminal:\n`bash gcloud auth application-default login`\n\nFor additional details, see the\n[ADC documentation](https://docs.cloud.google.com/docs/authentication/application-default-credentials#personal).\n\n## Install the extension\n\nTo install the extension, run the following command in your terminal:\n\n```bash\ngemini extensions install https://github.com/gemini-cli-extensions/cloud-composer\n```\n\n## Available tools\n\nTo see a complete list of available tools and their schemas, see the\n[Cloud Composer MCP reference](https://docs.cloud.google.com/composer/docs/reference/mcp).\n\n## Sample use cases\n\nThe following are example use cases for the Cloud Composer MCP server:\n\n### Describe environment status\n\nIn this sample use case, you ask questions about environments in your project.\n\n`Find all Managed Airflow environments in us-central1 that aren't in the running\nstate at the moment. If any of them are in the error state, tell me the time\nwhen this environment was last updated and the environment's workloads\nconfiguration.`\n\n**Workflow**: Describing Managed Airflow environments might look like the\nfollowing.\n\n-   **View the environments list**: The agent uses `list_environments` to obtain\n    the list of environments in the specified region, along with information\n    about the last update time.\n\n### Create a new Managed Airflow environment with custom PyPI packages\n\nIn this sample use case, you create a new Managed Airflow environment and then\ninstall custom PyPI packages into it.\n\n`Create a new Managed Airflow (Gen 3) environment with Airflow 2 in my project.\nThen install the nltk[machine_learning] package to it. Use the\nexample-account@example-project.iam.gserviceaccount.com service account for the\nenvironment.`\n\n**Workflow**: Creating a new Managed Airflow environment and then installing\ncustom PyPI packages into it might look like the following.\n\n-   **Create an environment**: The agent uses `create_environment` to create a\n    new environment with the provided configuration parameters. The agent asks\n    about additional configuration parameters such as the list of IP addresses\n    that are allowed to access the Airflow UI.\n\n-   **Install packages**: The agent calls `manage_pypi_packages` to install the\n    specified PyPI package.\n\n### Troubleshooting failed DAG runs and tasks\n\n`Check the example-environment-name Managed Airflow environment in us-central1.\nThe example_dag is failing, and I want to know why and at which task\nspecifically. Also tell me about any other DAGs that failed in this environment\nin the past 24 hours.`\n\n**Workflow**: Troubleshooting failed DAG runs might look like the following.\n\n-   **Get failed DAG runs**: The agent uses `find_last_failed_dag_runs` to\n    obtain the list of failed DAG runs for the example_dag DAG in the specified\n    environment. The agent uses the same tool to obtain the list of all failed\n    DAG runs.\n\n-   **Inspect the failed DAG run**: The agent calls `list_failed_task_instances`\n    to get the list of task instances of the DAG run that are in the failed\n    state.\n\n-   **Analyze failed task logs**: The agent uses `get_task_instance` to obtain\n    the details of the failed task instance, including data required to retrieve\n    logs.\n\n-   **Inspect the DAG source code**: The agent uses `get_dag_source_code` to\n    analyze the failed task source code for errors.\n\n## Optional security and safety configurations\n\nMCP introduces new security risks and considerations due to the wide variety of\nactions that you can take with MCP tools. To minimize and manage these risks,\nGoogle Cloud offers defaults and customizable policies to control the use of MCP\ntools in your Google Cloud organization or project. For more information about\nMCP security and governance, see\n[AI security and safety](https://docs.cloud.google.com/mcp/ai-security-safety).\n\n## Quotas and limits\n\nThe Cloud Composer MCP server doesn't have its own quotas. There is no limit on\nthe number of calls that can be made to the MCP server. You are still subject to\nthe quotas enforced by the APIs called by the MCP server tools.\n\n## Reference and resources\n\n*   Explore the\n    [Cloud Composer remote MCP server reference documentation](https://docs.cloud.google.com/composer/docs/reference/mcp),\n    which includes a list of all available tools, and the full input and output\n    schema for each tool.\n*   See the\n    [Cloud Composer overview](https://docs.cloud.google.com/composer/docs/concepts/overview).\n*   Learn about\n    [MCP security and governance](https://docs.cloud.google.com/mcp/ai-security-safety).\n",
  "bytes": 6543,
  "sha": "caede99711a4775d607a8ec0c0cc18230acc9deee25873d2068bd5feb00eac69",
  "repo_slug": "gemini-cli-extensions/cloud-composer",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_gemini_cli_extensions_cloud_composer_938cf244/readme"
}