Server facts
Cloud Run MCP Server
Project
- Author
- GoogleCloudPlatform
- License
- Apache-2.0
- Category
- Cloud & DevOps
Tech
- Runtime / language
- node
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 633
- Last commit
- Data as of
Tags
- App Deployment
- Cloud Run
- Gemini Cli
- Google Cloud
- Service Logs
Overview
Where this server runs affects what an agent can do with it. A local instance can deploy a source folder and discover Google Cloud projects, or create a project connected to the first available billing account. Those operations are marked local-only. File-content deployment and service inspection form the other tool group: agents can submit application files directly, list services for a selected region and project, inspect one service, or retrieve its logs and errors. The repository also supplies deploy and logs prompts, with service naming drawn from a configured default or the working directory. Gemini CLI has an extension installation path alongside ordinary MCP client configuration.
The README recommends a local Node setup using the Cloud SDK and application-default credentials. Docker is documented as another local option. Alternatively, the MCP process can itself be deployed to Cloud Run with IAM authentication and a proxy running on the user's machine. Remote operation must not be left unauthenticated, and deployment targets are restricted to the project hosting that server. OAuth is described as an additional authentication mechanism. Configuration can set defaults for service, region, and project. It also exposes security-related switches: Host-header validation is off initially, and the separate service IAM-check setting defaults to skipping checks. These defaults are not a substitute for securing access to the remote MCP process. The repository distinguishes its deployment tools from separate documentation on hosting arbitrary MCP servers.
Install & configure
Requirements
- Node.js, preferably an LTS release
- Installed Google Cloud SDK
- Google account authentication and application-default credentials
- MCP client configured to start the local package
npx -y @google-cloud/cloud-run-mcpThe command matches the README's recommended local Node configuration, not the bare script from config_hint. Prepare credentials with gcloud auth login followed by gcloud auth application-default login. All three environment entries are optional defaults. A remotely hosted server follows a different authenticated setup and does not expose the local-only tools.
Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"cloud-run-mcp": {
"command": "npx",
"args": [
"-y",
"@google-cloud/cloud-run-mcp"
],
"env": {
"GOOGLE_CLOUD_PROJECT": "<optional project ID used when a request omits it>",
"GOOGLE_CLOUD_REGION": "<optional deployment region used by default>",
"DEFAULT_SERVICE_NAME": "<optional fallback name for the Cloud Run service>"
}
}
}
}Config file · Project: .cursor/mcp.json
User: ~/.cursor/mcp.json
The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"cloud-run-mcp": {
"command": "npx",
"args": [
"-y",
"@google-cloud/cloud-run-mcp"
],
"env": {
"GOOGLE_CLOUD_PROJECT": "<optional project ID used when a request omits it>",
"GOOGLE_CLOUD_REGION": "<optional deployment region used by default>",
"DEFAULT_SERVICE_NAME": "<optional fallback name for the Cloud Run service>"
}
}
}
}Config file · Workspace: .vscode/mcp.json
For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.
{
"servers": {
"cloud-run-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@google-cloud/cloud-run-mcp"
],
"env": {
"GOOGLE_CLOUD_PROJECT": "<optional project ID used when a request omits it>",
"GOOGLE_CLOUD_REGION": "<optional deployment region used by default>",
"DEFAULT_SERVICE_NAME": "<optional fallback name for the Cloud Run service>"
}
}
}
}Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json
Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json
Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"cloud-run-mcp": {
"command": "npx",
"args": [
"-y",
"@google-cloud/cloud-run-mcp"
],
"env": {
"GOOGLE_CLOUD_PROJECT": "<optional project ID used when a request omits it>",
"GOOGLE_CLOUD_REGION": "<optional deployment region used by default>",
"DEFAULT_SERVICE_NAME": "<optional fallback name for the Cloud Run service>"
}
}
}
}Config file · Project scope: .mcp.json at the repository root
The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"cloud-run-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@google-cloud/cloud-run-mcp"
],
"env": {
"GOOGLE_CLOUD_PROJECT": "<optional project ID used when a request omits it>",
"GOOGLE_CLOUD_REGION": "<optional deployment region used by default>",
"DEFAULT_SERVICE_NAME": "<optional fallback name for the Cloud Run service>"
}
}
}
}Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Tools
Source: repository README. Tool descriptions are a documented snapshot, not a live capability check.
| Tool | What it does |
|---|---|
| get-service-log | Read a selected service's logs, including error messages. |
| get-service | Inspect details about one deployed Cloud Run service. |
| list-services | Discover services within the chosen region and project. |
| deploy-file-contents | Publish an application by supplying its files' contents directly. |
| deploy-local-folder | Use a source directory for deployment; exposed only by a locally running instance. |
| list-projects | Discover available Google Cloud projects in local mode. |
| create-project | In local mode, create a project linked to the first available billing account, optionally choosing its ID. |
Names, permissions, and defaults can change. Check the current upstream documentation before granting access.
Use cases
- Move application source from an agent workflow into a Cloud Run deployment.
- Inspect service configuration and error evidence after deployment.
- Use saved deployment defaults with the supplied deploy and logs prompts.
- Discover or create Google Cloud projects when operating the server locally.
Strengths
- Keeps deployment, service lookup, and log retrieval in one agent-facing interface.
- Documents Node, Docker, Gemini CLI, and authenticated remote connection paths.
- Distinguishes local-only project and folder operations from other tools.
Limitations
- Remote instances cannot deploy outside their own hosting project.
- Folder deployment and project discovery or creation are unavailable in remote mode.
- Remote access needs authentication; host validation is not enabled by default.
Frequently asked questions
Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.
