home / mcp / google cloud mcp server

Google Cloud MCP Server

🤖 A Model Context Protocol (MCP) server for Google Cloud (GCP)

Installation
Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "krzko-google-cloud-mcp": {
      "command": "node",
      "args": [
        "/Users/foo/code/google-cloud-mcp/dist/index.js"
      ],
      "env": {
        "GOOGLE_PRIVATE_KEY": "YOUR_PRIVATE_KEY",
        "GOOGLE_CLIENT_EMAIL": "YOUR_CLIENT_EMAIL",
        "GOOGLE_APPLICATION_CREDENTIALS": "/Users/foo/.config/gcloud/application_default_credentials.json"
      }
    }
  }
}

This Google Cloud MCP Server lets you connect to Google Cloud services to retrieve context and perform actions on resources such as Billing, IAM, Logging, Monitoring, Spanner, and more. It enables natural-language interactions to query data, run analyses, and execute cloud operations from a single MCP client.

How to use

You interact with Google Cloud resources by running natural-language prompts through your MCP client. Start by configuring the server connection in your client with the stdio workflow described here, then ask for concrete tasks like listing Spanner databases, querying IAM policies, or fetching error trends. Use straightforward prompts such as: “Show me billing accounts,” “List Spanner databases in my instance,” or “Analyse costs for project my-app-prod-123 for the last 30 days.” The server translates your natural language into Google Cloud API calls and returns structured results or suggested actions.

How to install

Prerequisites you need before installing this MCP server: a current Node.js environment, a JavaScript/TypeScript project setup, and access to Google Cloud credentials.

Install steps you should follow exactly:

  • Clone the repository to your development machine
  • Install dependencies with your preferred package manager
  • Build the project to produce the runtime artifacts
  • Authenticate to Google Cloud before first use

Additional setup and configuration

Configure authentication so the server can access Google Cloud resources. You have two options: provide a Service Account Key File and set the GOOGLE_APPLICATION_CREDENTIALS environment variable, or export the individual credentials via GOOGLE_CLIENT_EMAIL and GOOGLE_PRIVATE_KEY. The server will also use GOOGLE_CLOUD_PROJECT if you set it.

A concrete example of starting the server locally after building it is shown in the snippet below. It runs the local Node process and points to the built entry script, with credentials supplied via an environment variable.

Authentication

Two methods are supported to authenticate with Google Cloud. Use a Service Account Key File by setting GOOGLE_APPLICATION_CREDENTIALS to the path of your key file, which is the recommended approach. Alternatively, you can set GOOGLE_CLIENT_EMAIL and GOOGLE_PRIVATE_KEY directly in the environment. The server will use GOOGLE_CLOUD_PROJECT if you set it.

Make sure the service account has the necessary permissions for the actions you plan to perform, and ensure that the credentials are accessible to the environment where the MCP server runs.

Troubleshooting

If you encounter issues starting or running the server, enable debugging, verify credentials are accessible, and check for authentication-related errors. Common steps include ensuring lazy authentication is configured if you want the server to authenticate only when needed, and confirming the credentials file contents are valid.

Available tools

gcp-billing-list-accounts

List all billing accounts available to your Google Cloud organization or user.

gcp-billing-get-account-details

Retrieve detailed information for a specific billing account.

gcp-billing-list-projects

List projects associated with a billing account.

gcp-billing-get-project-info

Fetch details about a specific project’s billing configuration.

gcp-billing-list-services

Show available billing services for a given scope.

gcp-billing-list-skus

List SKUs (pricing components) for billing analysis.

gcp-billing-analyse-costs

Analyse costs across projects or time ranges to identify optimization opportunities.

gcp-billing-detect-anomalies

Detect unusual cost patterns that may indicate misconfigurations or anomalies.

gcp-billing-cost-recommendations

Provide recommendations to reduce or optimize billing costs.

gcp-billing-service-breakdown

Break down costs by service within a billing account.

gcp-error-reporting-list-groups

List error groups reported by your Google Cloud projects.

gcp-error-reporting-get-group-details

Get detailed information for a specific error group.

gcp-error-reporting-analyse-trends

Analyse error trends over time across services.

gcp-iam-get-project-policy

Retrieve the IAM policy for a project.

gcp-iam-test-project-permissions

Test whether you have specific permissions on a project.

gcp-iam-test-resource-permissions

Test whether you have permissions on a resource.

gcp-iam-validate-deployment-permissions

Validate if required permissions are in place for deployment.

gcp-iam-list-deployment-services

List services involved in a deployment context.

gcp-iam-analyse-permission-gaps

Identify gaps in permissions necessary for operations.

gcp-logging-query-logs

Query log entries from Google Cloud Logging.

gcp-logging-query-time-range

Query logs over a specified time range.

gcp-logging-search-comprehensive

Perform comprehensive log searches with filters.

gcp-spanner-execute-query

Execute SQL queries against Spanner databases.

gcp-spanner-list-tables

List tables within a Spanner database.

gcp-spanner-list-instances

List Spanner instances in your project.

gcp-spanner-list-databases

List databases within a Spanner instance.

gcp-spanner-query-natural-language

Query Spanner using natural language prompts.

gcp-spanner-query-count

Return count results for a Spanner query.

gcp-monitoring-query-metrics

Query Google Cloud Monitoring metrics.

gcp-monitoring-list-metric-types

List available metric types in a project.

gcp-monitoring-query-natural-language

Query monitoring data using natural language.

gcp-profiler-list-profiles

List CPU/profile data captured by Cloud Profiler.

gcp-profiler-analyse-performance

Analyse performance profiling results.

gcp-profiler-compare-trends

Compare profiling trends across deployments.

gcp-trace-get-trace

Get details for a distributed trace.

gcp-trace-list-traces

List traces for a project.

gcp-trace-find-from-logs

Find traces related to specific logs.

gcp-trace-query-natural-language

Query traces using natural language prompts.