GCP

Provides natural language access to GCP resources by running a local MCP server that uses your GCP credentials to query and manage resources.

typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "radiumgu-gcp-ops-mcp": {
      "command": "node",
      "args": [
        "/path/to/gcp-ops-mcp/bin.js"
      ],
      "env": {
        "NODE_PATH": "/path/to/gcp-ops-mcp/node_modules"
      }
    }
  }
}

You can use this MCP server to let an AI assistant interact with your Google Cloud Platform environment through natural language queries and actions. It enables querying and managing GCP resources across projects and regions without writing API calls yourself, while keeping credentials securely local.

How to use

Start by choosing an MCP client (Claude Desktop, Cursor, Windsurf, or an Amazon Q CLI) and connect it to the GCP MCP server using the provided local command configurations. Once connected, you can ask questions like which GCP projects you have access to, list resources such as Cloud SQL instances or GKE clusters, check billing info, view logs, and more. Your assistant will execute the corresponding GCP API calls locally, using your credentials, and return results in the chat.

How to install

Prerequisites: you need Node.js installed locally and GCP credentials configured (application default credentials). Ensure you have access to the projects and APIs you plan to query.

Steps to install and run the MCP server locally:

Clone the project repository to your local machine.

Install dependencies.

Build the project.

Configuration and usage notes

Configure your MCP client to run the MCP server as shown below. You can choose different methods to start the local MCP server depending on the client you use.

Security and credentials

Credentials are handled locally on your machine. No credentials are exposed to external services. Make sure your environment keeps credentials secure and rotate credentials as needed.

Troubleshooting

If you encounter authentication or permission errors, verify that you have run the appropriate gcloud commands to set up application-default credentials and that IAM roles grant the necessary access. Ensure required APIs are enabled for your project.

Usage examples (high level)

Examples of questions you can ask include:

List all GCP projects you have access to
Show me all Cloud SQL instances in a specific project
What is my current billing status?
Show me logs from my Cloud Run services
List all GKE clusters in a region
Show me Cloud Storage buckets in a project
What Cloud Functions are deployed in a region?
List all Cloud Run services
Show me BigQuery datasets and tables

Available tools

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.