Mcp Server Gcp Manager

What is Mcp Server Gcp Manager?

Mcp Server Gcp Manager is an open-source Model Context Protocol (MCP) server that enables AI agents (such as Claude, Llama 3.1, or custom LangChain bots) to interact with Google Cloud Platform safely and autonomously. It bridges an LLM with the gcloud CLI, allowing natural‑language management of Cloud Run services and Google Secret Manager.

How to use Mcp Server Gcp Manager?

Installation requires Python 3.10+, a working gcloud installation authenticated with a project, and the mcp Python package. Optionally set the GCLOUD_PATH environment variable if gcloud is not auto‑detected. For Claude Desktop, add a gcp-manager entry to claude_desktop_config.json. For LangChain or custom agents, use langchain-mcp-adapters to connect to the server via stdio transport.

Key features of Mcp Server Gcp Manager

• List Cloud Run services with detailed inspection.
• Create and update secrets in Google Secret Manager.
• Automatically enable the Secret Manager API if disabled.
• Deploy new Cloud Run revisions (update memory, image, etc.).
• Check existing configuration before applying changes to prevent accidental overwrites.

Use cases of Mcp Server Gcp Manager

• List all running Cloud Run services in a GCP project.
• Safely create or update secrets using natural language.
• Deploy a new Cloud Run revision with custom memory or image settings.

FAQ from Mcp Server Gcp Manager

What are the prerequisites?

Python 3.10 or later, and the Google Cloud SDK (gcloud) installed and authenticated. On macOS, install via brew install --cask google-cloud-sdk. Authenticate with gcloud auth login and set your project with gcloud config set project [YOUR_PROJECT_ID].

How do I configure the path to gcloud?

The server auto‑detects gcloud. If it fails, set the environment variable GCLOUD_PATH to the full path of the gcloud executable (e.g., /usr/local/bin/gcloud on Mac/Linux or the Windows equivalent).

How do I use this server with Claude Desktop?

Add a gcp-manager entry to your claude_desktop_config.json specifying the Python interpreter and the path to server.py. Example: "command": "/path/to/venv/bin/python", "args": ["/path/to/mcp-gcp-manager/server.py"].

What tools are available?

Three tools: list_running_services (list Cloud Run services), create_secret (create/update secrets, auto‑enabling Secret Manager API), and deploy_service (deploy new revisions with memory/image updates).

How do I install dependencies?

Clone the repository, create a Python virtual environment, activate it, and run pip install mcp.