Cloud Run MCP Server
A secure MCP server example that demonstrates how to deploy to Google Cloud Run with authentication and identity token protection. Serves as a tutorial template for building production-ready MCP servers in the cloud.
What is Cloud Run MCP Server?
Cloud Run MCP Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to secure mcp server example that demonstrates how to deploy to google cloud run with authentication and identity token protection. serves as a tutorial template for building production-ready mcp servers...
A secure MCP server example that demonstrates how to deploy to Google Cloud Run with authentication and identity token protection. Serves as a tutorial template for building production-ready MCP servers in the cloud.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A secure MCP server example that demonstrates how to deploy
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @google-cloud/cloud-run-mcpManual Installation
npx -y @google-cloud/cloud-run-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Cloud Run MCP Server
The Cloud Run MCP Server is an official Google Cloud example and reference implementation that lets AI assistants deploy code directly to Google Cloud Run, list running services, retrieve logs, and manage GCP projects through natural language commands. It ships as the @google-cloud/cloud-run-mcp npm package and can run locally via npx, inside Docker, or as a deployed Cloud Run service with identity token authentication. DevOps engineers and cloud developers use it to deploy web services, check service health, and iterate on Cloud Run workloads without leaving their AI assistant.
Prerequisites
- Node.js LTS (18 or later) installed, or Docker for the container-based setup
- Google Cloud SDK (gcloud) installed and authenticated via 'gcloud auth login'
- Application Default Credentials configured with 'gcloud auth application-default login'
- A GCP project with the Cloud Run API enabled and appropriate IAM roles (Cloud Run Admin or equivalent)
- An MCP client such as Claude Desktop or the Gemini CLI
Authenticate with Google Cloud
Log in with the gcloud CLI and set up application default credentials so the MCP server can call Cloud Run APIs on your behalf.
gcloud auth login
gcloud auth application-default login
gcloud config set project YOUR_PROJECT_IDRun the server locally with npx
Start the MCP server using npx without a global install. It reads your application default credentials automatically.
npx -y @google-cloud/cloud-run-mcpConfigure Claude Desktop
Add the server to your Claude Desktop configuration file so it starts automatically. Use the GOOGLE_CLOUD_PROJECT and GOOGLE_CLOUD_REGION environment variables to set defaults.
Enable IAM check control (optional)
By default SKIP_IAM_CHECK is true. Set it to false in production deployments to enforce IAM permission validation before running Cloud Run operations.
Deploy the server to Cloud Run itself (optional)
For team or production use, deploy the MCP server as a Cloud Run service with identity token authentication so no local credentials are needed by end users.
gcloud run deploy cloud-run-mcp \
--image us-docker.pkg.dev/cloudrun/container/mcp \
--no-allow-unauthenticated \
--region us-central1Cloud Run MCP Server Examples
Client configuration
Claude Desktop configuration for the Cloud Run MCP Server using npx with default project and region set via environment variables.
{
"mcpServers": {
"cloud-run-mcp": {
"command": "npx",
"args": ["-y", "@google-cloud/cloud-run-mcp"],
"env": {
"GOOGLE_CLOUD_PROJECT": "your-gcp-project-id",
"GOOGLE_CLOUD_REGION": "us-central1",
"SKIP_IAM_CHECK": "true"
}
}
}
}Prompts to try
Natural-language commands for deploying and managing Cloud Run services.
- "Deploy the current working directory to Cloud Run as service my-api in us-central1"
- "List all Cloud Run services in project my-project and show their URLs and status"
- "Get the last 50 log lines from the service named backend-service"
- "Deploy the folder /home/user/app as a new Cloud Run service called hello-world"
- "What is the current revision of the service api-gateway and when was it last deployed?"Troubleshooting Cloud Run MCP Server
API returns 'Permission denied' when listing or deploying services
Verify your authenticated account has the Cloud Run Admin or Cloud Run Developer IAM role on the project. Run 'gcloud projects get-iam-policy YOUR_PROJECT' to check. Also confirm the Cloud Run API is enabled with 'gcloud services enable run.googleapis.com'.
Application default credentials not found
Run 'gcloud auth application-default login' to create the credentials file. The MCP server reads these automatically. If running in Docker, mount the credentials file and set GOOGLE_APPLICATION_CREDENTIALS to point to it.
npx hangs or fails with EACCES errors
Ensure Node.js LTS is installed and the npx binary is on your PATH. On macOS, install Node via Homebrew ('brew install node') to avoid permission issues with system Python or npm global installs.
Frequently Asked Questions about Cloud Run MCP Server
What is Cloud Run MCP Server?
Cloud Run MCP Server is a Model Context Protocol (MCP) server that secure mcp server example that demonstrates how to deploy to google cloud run with authentication and identity token protection. serves as a tutorial template for building production-ready mcp servers in the cloud. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Cloud Run MCP Server?
Install via npm with the command: npx -y @google-cloud/cloud-run-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Cloud Run MCP Server?
Cloud Run MCP Server works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Cloud Run MCP Server free to use?
Yes, Cloud Run MCP Server is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Cloud Run MCP Server Alternatives — Similar Cloud Services Servers
Looking for alternatives to Cloud Run MCP Server? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Cloud Run MCP Server in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Cloud Run MCP Server?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.