GCP

Provides a structured MCP server for querying and managing Google Cloud Platform resources via AI-assisted interactions.

python

GitHub Stars

python

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-enesbol_gcp-mcp": {
      "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": {
        "GCP_LOCATION": "us-central1",
        "GCP_PROJECT_ID": "your-gcp-project-id",
        "GOOGLE_APPLICATION_CREDENTIALS": "C:/path/to/credentials.json"
      }
    }
  }
}

You can run a GCP-focused MCP Server that lets AI assistants query and manage Google Cloud resources through a standardized interface. This server helps you automate work across GCP services while enforcing secure access and consistent interactions.

How to use

You interact with the GCP MCP Server through an MCP client. The server exposes capabilities to query GCP resources, manage cloud services, and receive AI-guided assistance for configurations and best practices. Start the server, connect your MCP client, and issue requests for specific services such as Artifact Registry, BigQuery, Cloud Run, Cloud Storage, and more. The client sends structured requests, and the server returns responses that you can use to drive automation, dashboards, or conversational prompts.

How to install

Prerequisites you need before installing the server are:

Python 3.10 or newer
A Google Cloud Project with APIs enabled for the services you plan to use
Authenticated GCP credentials (Application Default Credentials recommended)

Steps to install and run the server locally:

Prepare a workspace and a dedicated Python environment
Install the MCP package and required GCP tooling
Configure credentials and environment variables
Start the MCP server with the appropriate runtime command

# Create and activate a virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install MCP package with required CLI tooling
pip install "mcp[cli]"

# Install GCP-specific tooling as needed by your configuration
# (Examples shown assume you follow typical setup; adapt to your environment)

# Run the MCP server using the provided runtime command (see configuration below)
uv 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 main.py
```} ,{

Additional configuration and security notes

Configuration is provided through environment variables and, where applicable, a configuration file. The server relies on Application Default Credentials for authentication and enforces authorization based on the permissions granted to the authenticated identity. No credentials are hardcoded in the server or service implementations. It is recommended to run with a service account that has the minimum necessary permissions for your use cases.

Environment variables commonly used with the GCP MCP Server include credentials and project/location context. Ensure these are securely stored and not checked into source control.

Troubleshooting and notes

If you encounter authentication or permission errors, verify that your Google Application Credentials point to a valid service account with the required roles for the APIs you enabled. Check that the project ID and location are correctly set in your environment. Review logs for any API access issues or quota limits.

Built by

VeilStrat

AI signals for GTM teams