GCP Cloud Tools MCP Server

How to use

You will interact with the GCP MCP Server using an MCP client. Start by ensuring your MCP client can reach the server and that you have the proper credentials for your GCP project. With the server running, you can ask it to query GCP resources, create or update cloud resources, and receive guided best-practice recommendations for configurations. The server handles authentication via your GCP credentials and enforces permissions based on the authenticated identity.

How to install

Prerequisites you need to satisfy before installation are: Python 3.10 or newer and access to a GCP project with the APIs you plan to use enabled. You should have a GCP service account key if you plan to authenticate with a key file.

Step by step commands to set up and run the server locally:

# 1) Install prerequisites (Python should be available on your system)
# 2) Create or clone the MCP server project if you already have it
# 3) Prepare a suitable environment (optional virtual env)

# 4) Run the MCP server (example stdio configuration will be provided in the Configuration section)

Additional steps and notes

For development and testing, you can run in dev mode or specify a configuration file to tailor the server behavior to your environment. Ensure your Google Cloud credentials are accessible to the server, either via a service account key file pointed to by GOOGLE_APPLICATION_CREDENTIALS or by using Application Default Credentials.

Configuration

The MCP server can be configured to run locally as a stdio (local) server. The following configuration shows how to launch the server using a stdio approach with the required environment variables and the complete command to start the runtime. This exact snippet should be placed in your MCP configuration under mcpServers.

{
  "mcpServers": {
    "GCP Cloud Tools": {
      "type": "stdio",
      "name": "gcp_cloud_tools",
      "command": "uv",
      "args": [
        "run",
        "--with",
        "google-cloud-artifact-registry>=1.10.0",
        "--with",
        "google-cloud-bigquery>=3.27.0",
        "--with",
        "google-cloud-build>=3.0.0",
        "--with",
        "google-cloud-compute>=1.0.0",
        "--with",
        "google-cloud-logging>=3.5.0",
        "--with",
        "google-cloud-monitoring>=2.0.0",
        "--with",
        "google-cloud-run>=0.9.0",
        "--with",
        "google-cloud-storage>=2.10.0",
        "--with",
        "mcp[cli]",
        "--with",
        "python-dotenv>=1.0.0",
        "mcp",
        "run",
        "C:\\Users\\enes_\\Desktop\\mcp-repo-final\\gcp-mcp\\src\\gcp-mcp-server\\main.py"
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "C:/Users/enes_/Desktop/mcp-repo-final/gcp-mcp/service-account.json",
        "GCP_PROJECT_ID": "gcp-mcp-cloud-project",
        "GCP_LOCATION": "us-east1"
      }
    }
  }
}

query_gcp_resources

Query and retrieve information about GCP resources across enabled services, returning structured results to assist planning and debugging.

manage_gcp_resources

Create, update, and configure GCP resources such as Compute Engine instances, Cloud Storage buckets, and BigQuery datasets through guided MCP commands.

assist_gcp_config

Provide AI-assisted guidance for GCP configurations, best practices, and security recommendations based on observed usage and policies.