Model Context Protocol

GCP MCP

Enable AI assistants like Claude to interact with your Google Cloud Platform environment through natural language.

terminal@gcp-mcp:~

Features

Powerful capabilities to enhance your AI assistant's interaction with GCP

Natural Language Querying

Query and modify GCP resources using natural language during conversations

Multi-Project Support

Seamlessly work with multiple GCP projects in the same conversation

Multi-Region Support

Access resources across different GCP regions with ease

Secure Credential Handling

No credentials are exposed to external services, keeping your data safe

Local Execution

Runs locally with your GCP credentials for maximum security

Automatic Retries

Built-in retry mechanism for improved reliability and performance

Installation

Get up and running with GCP MCP in minutes

Prerequisites

Node.js
Claude Desktop/Cursor/Windsurf
GCP credentials configured locally (application default credentials)

Claude Desktop

Open Claude desktop app and go to Settings -> Developer -> Edit Config

Add the following entry to your claude_desktop_config.json:

{
  "mcpServers": {
    "gcp": {
      "command": "sh",
      "args": ["-c", "npx -y gcp-mcp"]
    }
  }
}

Step 1: Clone the repository

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

Step 2: Install dependencies

npm install

Step 4: Set up GCP credentials

Set up application default credentials:

gcloud auth application-default login

Refresh your AI assistant (Claude Desktop/Cursor/Windsurf)

Usage

Start interacting with your GCP environment through natural language

Start by selecting a project or asking questions like:

"List all GCP projects I have access to"

"Show me all Cloud SQL instances in project X"

"What's my current billing status?"

"Show me the logs from my Cloud Run services"

"List all GKE clusters in us-central1"

"Show me all Cloud Storage buckets in project X"

Interactive Demo

Try out GCP MCP commands in this interactive demo

interactive-demo@gcp-mcp:~

Welcome to the GCP MCP interactive demo. Try out some commands:

Available Tools

Powerful tools to interact with your GCP environment

run-gcp-code

Execute GCP API calls using TypeScript code

list-projects

List all accessible GCP projects

select-project

Select a GCP project for subsequent operations

get-billing-info

Get billing information for the current project

get-cost-forecast

Get cost forecast for the current project

get-billing-budget

Get billing budgets for the current project

list-gke-clusters

List all GKE clusters in the current project

list-sql-instances

List all Cloud SQL instances in the current project

get-logs

Get Cloud Logging entries for the current project

Supported Services

GCP MCP supports a wide range of Google Cloud Platform services

Google Compute Engine

Cloud Storage

Cloud Functions

Cloud Run

BigQuery

Cloud SQL

Google Kubernetes Engine

Cloud Logging

Cloud Billing

Resource Manager

More coming soon...

Troubleshooting

Common issues and how to resolve them

Viewing Logs

To see logs:

tail -n 50 -f ~/Library/Logs/Claude/mcp-server-gcp.log

Common Issues

Authentication errors

Ensure you've run gcloud auth application-default login

Permission errors

Check IAM roles for your account

API errors

Verify that required APIs are enabled in your project