mcpField
G
Google Cloud MCP Server

Google Cloud MCP Server

Local
github.com/lreimerCloud & Infra4Updated 77w ago

About Google Cloud MCP Server

A Google Cloud MCP server implemented in Go with Cobra. It supports stdio and SSE transports and provides list and describe operations for projects, Container clusters, and Cloud Run services.

Key features

  1. 01stdio and SSE transports
  2. 02List and describe projects
  3. 03List and describe clusters
  4. 04List and describe Cloud Run services

Use cases

  1. 01Review Google Cloud project details
  2. 02Inspect Container clusters and Cloud Run services

MCP support

The MCP server exposes list and describe operations for Google Cloud projects, Container clusters, and Cloud Run services over stdio or SSE.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"gcp": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/inspector"
]
}
}
}
Run commandnpx -y @modelcontextprotocol/inspector

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@modelcontextprotocol/inspector

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Google Cloud MCP Server

A MCP server implementation for Google Cloud using Go and Cobra. The server supports stdio as well as SSE as transport. The following services and operations have been implemented:

  • Projects: Projects List, Project Describe
  • Container: Clusters List, Cluster Describe
  • Cloud Run: Services List, Service Describe

Build and Release

goreleaser build --snapshot --clean
goreleaser release --skip=publish --snapshot --clean

Usage Instructions

If you want to use the tool locally, e.g. with Claude Desktop, use the following configuration for the MCP server.

{
    "mcpServers": {
      "gcloud": {
        "command": "/Users/mario-leander.reimer/Applications/gcp-mcp-server",
        "args": ["--transport", "stdio"],
        "env": {
        }
      }
    }
}

Alternatively, you can use the MCP introspector for easy local development:

# as stdio binary
npx @modelcontextprotocol/inspector go run main.go

# as SSE server using 
go run main.go --transport sse
npx @modelcontextprotocol/inspector npx mcp-remote@next http://localhost:8000/sse
npx @modelcontextprotocol/inspector

Deployment

Currently using manual Google Cloud Run deployment. Can either be deployed directly from source or using the Docker image built on Github.

# make sure to enable all required APIs
gcloud services enable secretmanager.googleapis.com
gcloud services enable cloudbuild.googleapis.com artifactregistry.googleapis.com
gcloud services enable run.googleapis.com 

# create Google service account with required permissions and create key file
export PROJECT_ID=$(gcloud config get-value project)
export SA_NAME=gcp-mcp-server-sa

gcloud iam service-accounts create $SA_NAME --display-name="GCP MCP Server Service Account"
gcloud projects add-iam-policy-binding $PROJECT_ID \
  --member="serviceAccount:$SA_NAME@$PROJECT_ID.iam.gserviceaccount.com" \
  --role="roles/editor"
gcloud iam service-accounts keys create $SA_NAME.json \
  --iam-account=$SA_NAME@$PROJECT_ID.iam.gserviceaccount.com

# create the keyfile as a secret and attach IAM policy
gcloud secrets create $SA_NAME --data-file=$SA_NAME.json
gcloud secrets add-iam-policy-binding $SA_NAME \
  --member=serviceAccount:[email protected] \
  --role=roles/secretmanager.secretAccessor

gcloud run deploy gcp-mcp-server --source=. \
  --region=europe-north1 \
  --port=8000 --allow-unauthenticated \
  --set-secrets=/secrets/gcp-mcp-server-sa.json=gcp-mcp-server-sa:latest \
  --set-env-vars=GOOGLE_APPLICATION_CREDENTIALS=/secrets/gcp-mcp-server-sa.json,BASE_URL=https://gcp-mcp-server-343509396461.europe-north1.run.app

gcloud run services delete gcp-mcp-server --async --region=europe-north1

Maintainer

M.-Leander Reimer (@lreimer), [email protected]

License

This software is provided under the MIT open source license, read the LICENSE file for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.