Cloud Run MCP server enables MCP-compatible AI agents to deploy apps to Google Cloud Run. This repository hosts an MCP server that can be configured in MCP clients (e.g., cloud-run with command npx and args -y @google-cloud/cloud-run-mcp). The server supports deployment from Gemini CLI, AI-powered IDEs, agent SDKs, and other MCP-enabled tools. It provides tooling to manage Cloud Run services, including deploy-file-contents (deploys files by content), list-services, get-service, get-service-log, deploy-local-folder (deploys a local folder), list-projects, and create-project. A recommended workflow is to run locally with Node.js or to deploy the server to Cloud Run with IAM-protected remote access. The remote setup uses gcloud auth, gcloud config, and gcloud run deploy to launch cloud-run-mcp with the image, plus optional environment variables. Documentation also covers prompts for common tasks (deploy, logs) and steps to install the Gemini CLI extension and configure MCP clients such as Windsurf, VSCode, Claude Desktop, and Cursor. IAM authentication is required for remote access to secure the deployment surface.