GCP MCP Server

A Model Context Protocol (MCP) server for Google Cloud Platform (GCP) that enables AI assistants to interact with GCP services, particularly focused on log analysis and root cause investigation.

Features

Cloud Logging Integration: Query and analyze GCP Cloud Logging data
Real-time Log Streaming: Stream logs for immediate analysis
Error Pattern Detection: Identify common error patterns and anomalies
Multi-Project Support: Work across multiple GCP projects
Secure Authentication: Uses GCP service account credentials
Root Cause Analysis: Tools to help with quick RC findings

Supported GCP Services

Cloud Logging: Query, filter, and analyze logs
Cloud Monitoring: Retrieve metrics and alerts (planned)
Error Reporting: Access error statistics and details (planned)
Cloud Trace: Distributed tracing analysis (planned)

Installation

⚡ Quick Install

git clone https://github.com/JayRajGoyal/gcp-mcp.git
cd gcp-mcp
./install.sh

Claude Code Integration (One Command!)

The easiest way to add this MCP server to Claude Code:

# If you have gcloud configured (recommended):
claude mcp add gcp-logs -e GOOGLE_APPLICATION_CREDENTIALS=/Users/$USER/.config/gcloud/application_default_credentials.json -- python3.11 -m gcp_mcp.cli --project YOUR_PROJECT_ID

Or with a service account key file:

claude mcp add gcp -- python3.11 -m gcp_mcp.cli --credentials /path/to/your/service-account-key.json

Manual Configuration (Alternative)

Add this to your Claude Code configuration:

{
  "mcpServers": {
    "gcp": {
      "command": "python3.11",
      "args": ["-m", "gcp_mcp.cli", "--credentials", "/path/to/your/credentials.json"],
      "cwd": "/path/to/gcp-mcp"
    }
  }
}

Prerequisites

Python 3.8 or higher
GCP project with appropriate APIs enabled
Service account with necessary permissions

Manual Setup

Clone the repository:

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

Install dependencies:

pip install -r requirements.txt

Run with your credentials:

python -m gcp_mcp.cli --credentials /path/to/your/credentials.json

Usage

Starting the Server

python -m gcp_mcp.server

Available Tools

Log Query

Query GCP Cloud Logging with advanced filters:

query_logs(project_id, filter, limit, time_range)

Log Analysis

Analyze logs for patterns and anomalies:

analyze_logs(project_id, service_name, time_range)

Error Investigation

Find and analyze error patterns:

investigate_errors(project_id, service_name, time_range)

Configuration

Create a config.json file:

{
  "default_project": "your-gcp-project-id",
  "log_retention_days": 30,
  "max_results": 1000,
  "excluded_log_names": [
    "projects/your-project/logs/cloudaudit.googleapis.com%2Fdata_access"
  ]
}

Authentication

The server supports multiple authentication methods:

Service Account Key File: Set GOOGLE_APPLICATION_CREDENTIALS
Application Default Credentials: For GCE, Cloud Shell, etc.
User Credentials: Via gcloud auth application-default login

Required GCP Permissions

Your service account needs the following IAM roles:

roles/logging.viewer - Read access to Cloud Logging
roles/monitoring.viewer - Read access to Cloud Monitoring (optional)
roles/errorreporting.viewer - Read access to Error Reporting (optional)

Development

Running Tests

pytest tests/

Code Formatting

black gcp_mcp/
isort gcp_mcp/

Type Checking

mypy gcp_mcp/

Contributing

Fork the repository
Create a feature branch
Make your changes
Add tests
Run the test suite
Submit a pull request

License

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

Security

Never commit service account keys to the repository
Use environment variables for sensitive configuration
Follow GCP security best practices
Report security vulnerabilities via email

Support

Create an issue for bug reports or feature requests
Check existing issues before creating new ones
Provide detailed information including logs and configuration

Roadmap