Google Cloud MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| analyse-errors | |
| trace-request | |
| performance-overview | |
| alert-investigation | |
| schema-explanation | |
| query-optimization | |
| data-exploration |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| resource-list | |
| spanner-resources | |
| logging-resources | |
| monitoring-resources |
TDQS
Scored across 17 tools
Most tools have distinct purposes targeting different Google Cloud services (Spanner, Cloud Trace, Cloud Monitoring, Cloud Logging), though some overlap exists between query tools like 'query-logs' and 'find-traces-from-logs' which might cause confusion. The natural language query tools for different services are clearly differentiated by their target domains.
The naming follows a mostly consistent verb-noun pattern with hyphens, but there are inconsistencies: 'get-project-id' and 'set-project-id' use a different structure than others, and some tools use compound nouns (e.g., 'natural-language-metrics-query') while others are simpler. The overall pattern is readable but mixed.
With 17 tools, the count is slightly high but reasonable for covering multiple Google Cloud services like Spanner, Trace, Logging, and Monitoring. It provides a comprehensive surface without being overwhelming, though it borders on the heavy side for a single server.
The tool set covers querying and listing operations for Spanner, Trace, Logging, and Monitoring, but lacks obvious CRUD operations (e.g., create/update/delete resources) and management functions. This creates gaps for full lifecycle management, though core query workflows are supported.