GCP

🚀 This is not a ready-to-use MCP Server for GCP

📌 GCP MCP Server

A comprehensive implementation of the Model Context Protocol (MCP) server, designed specifically for Google Cloud Platform (GCP) services. It enables AI assistants to interact with and manage GCP resources through a standardized interface.

🌟 Overview

The GCP MCP Server empowers AI assistants with the following capabilities:

• Query GCP resources
• Manage GCP resources
• Operate GCP resources

Supported services include:

• Artifact Registry: Asset registry
• BigQuery: Big query
• Build: Build
• Cloud Functions: Cloud functions
• Compute: Compute
• Logging: Logging
• Monitoring: Monitoring
• Run: Run
• Storage: Storage

🏗️ Architecture

The project's architecture consists of the following components:

• Core functions: Include logging, exception handling, and configuration management.
• Service modules: Each GCP service corresponds to an independent module.
• Client instance management: Responsible for creating and destroying GCP client instances.

🚀 Quick Start

Prerequisites

1. Install Python and pip.
2. Download and install Google Cloud SDK.

Installation Steps

1. Clone the repository:

   git clone https://github.com/yourusername/gcp-mcp-server.git
   cd gcp-mcp-server
   

2. Install dependencies:

   pip install -r requirements.txt
   

Environment Configuration

Add the following content to the config.json file:

{
  "GOOGLE_APPLICATION_CREDENTIALS": "path/to/service-account-key.json",
  "GCP_PROJECT_ID": "your-gcp-project-id",
  "GCP_LOCATION": "us-east1"
}

Start the Server

python main.py

🐳 Docker Deployment

Create a Dockerfile:

FROM python:3.9-slim

WORKDIR /app

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY . .

CMD ["python", "main.py"]

Build and run the image:

docker build -t gcp-mcp-server .
docker run -it --rm -v $(pwd)/config.json:/app/config.json gcp-mcp-server

⚙️ Configuration Options

The following parameters can be set in the config.json file:

• GOOGLE_APPLICATION_CREDENTIALS: Path to the GCP service account key.
• GCP_PROJECT_ID: GCP project ID.
• GCP_LOCATION: GCP region, default is "us-east1".

🛠️ Developing New GCP Services

To develop a new GCP service module, refer to the existing implementations in the services/ directory and follow these steps:

1. Create a new service module.
2. Implement interface methods.
3. Register the service provider.
4. Update documentation and examples.

⚠️ Security Considerations

• Credential management: Use environment variables or encrypted storage to manage GCP credentials.
• Access control: Restrict access to the MCP server to prevent unauthorized operations.
• Audit logging: Log all API calls for subsequent review.

🤝 Contribution Guidelines

1. Fork the repository.
2. Create a feature branch.
3. Commit your changes.
4. Push to the remote repository.
5. Submit a Pull Request.

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

🙏 Acknowledgments

Thanks to the contributions of the following teams and projects:

• The Google Cloud Platform team for providing rich APIs.
• The Model Context Protocol team for establishing a standardized interaction method.

💻 Usage Instructions

The steps to use this server are as follows:

1. Name the GCP service account key file service-account.json and place it in the current directory.
2. Install the MCP package:

   pip install "mcp[cli]"
   

3. Install the required GCP packages:

   pip install google-cloud-run
   

4. Start the server:

   mcp dev gcp_cloudrun_server.py
   

Alternatively, install it in Claude Desktop:

mcp install gcp_cloudrun_server.py --name "GCP Cloud Run Manager"

⚙️ MCP Server Configuration

Add the following configuration to your MCP configuration file to enable GCP cloud tools:

"mcpServers": {
  "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>=1.6.0",
      "--with",
      "google-cloud-functions>=2.24.0",
      "--with",
      "google-cloud-storage>=1.38.0"
    ]
  }
}

Thank you for using the GCP MCP Server! If you need help or feedback, please contact the maintenance team.