[ MCP SERVER SUMMARY ]
Google Cloud Run MCP server summary
Deploy code to Google Cloud Run Connect Google Cloud Run through Bifrost MCP Gateway to centralize access control, virtual keys, and tool-call observability for your AI assistants.
| Property | Details |
|---|---|
| Company | Upstream maintainer |
| Connection type | Confirm upstream transport |
| Authentication | Varies by upstream server |
| Package or endpoint | See upstream documentation |
| Capabilities | Google Cloud Run tools over MCP, AI assistant connectivity, Governed tool access through Bifrost |
| Official documentation | Google Cloud Run MCP documentation |
Before you start
- Review the Google Cloud Run upstream documentation for its installation requirements
- Obtain any credentials required by the upstream service
- A running Bifrost MCP Gateway instance
What you can do with Google Cloud Run
- Deploy code to Google Cloud Run
- Expose Google Cloud Run tools to Claude, Cursor, and other MCP clients through one endpoint
- Apply virtual keys, tool allowlists, and audit logging at the gateway
[ HOW TO CONNECT ]
Connect Google Cloud Run to Bifrost in three steps
Install Bifrost
Start the gateway locally or deploy in your VPC.
npx -y @maximhq/bifrost
Add Google Cloud Run in MCP Gateway
Open MCP Gateway in the Bifrost dashboard, click New MCP Server, and select the transport documented by the upstream server. Or register via the API below.
• Confirm the transport, command or endpoint, and authentication requirements in the Google Cloud Run upstream documentation.
• Replace every placeholder in the example before sending the request.
Point clients at Bifrost /mcp
Configure Claude Desktop, Cursor, or Claude Code to use your Bifrost endpoint with a virtual key instead of connecting directly to Google Cloud Run.
{
"mcpServers": {
"bifrost": {
"url": "http://localhost:8080/mcp",
"headers": {
"Authorization": "Bearer vk_your_virtual_key"
}
}
}
}[ EXAMPLE CONFIG ]
Register Google Cloud Run via API
Add this MCP client with a POST to /api/mcp/client. See Connecting to MCP Servers for full options.
# For a remote HTTP or SSE server:
curl -X POST http://localhost:8080/api/mcp/client \
-H "Content-Type: application/json" \
-d '{
"name": "google-cloud-run",
"connection_type": "<http|sse>",
"connection_string": "<upstream MCP endpoint>",
"tools_to_execute": ["*"]
}'
# For a local STDIO server:
curl -X POST http://localhost:8080/api/mcp/client \
-H "Content-Type: application/json" \
-d '{
"name": "google-cloud-run",
"connection_type": "stdio",
"stdio_config": {
"command": "<upstream command>",
"args": ["<arg>"]
},
"tools_to_execute": ["*"]
}'[ WHY BIFROST ]
Run Google Cloud Run through one governed gateway
Access control
Virtual keys, RBAC, and tool allowlists per team or agent.
Cost governance
Attribute MCP tool spend alongside LLM usage in one view.
Observability
Log every tool call with latency, server, and virtual key metadata.
Credential isolation
Upstream secrets stay in the gateway — not on every laptop.
[ FAQ ]
Common questions
What does the Google Cloud Run MCP server do?
Deploy code to Google Cloud Run The exact tools available depend on the upstream server version and configuration.
How do I connect Google Cloud Run to Bifrost?
Check the upstream documentation to determine whether Google Cloud Run uses STDIO, Streamable HTTP, or SSE. Then add it as an MCP client in Bifrost using the corresponding command or endpoint.
Does Bifrost replace the Google Cloud Run MCP server?
No. Bifrost connects to Google Cloud Run as an upstream MCP client and adds a governed gateway between that server and your AI assistants.
[ RELATED SERVERS ]
More MCP integrations
GoLogin MCP server
Manage your GoLogin browser profiles and automation directly through AI conversations!
Google Calendar
Let AI assistants access Google Calendar events and automate scheduling workflows through Google Workspace MCP.
Google Chat
Enable AI assistants to work with Google Chat spaces, messages, and collaboration workflows through Google Workspace MCP.