Google Cloud MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GOOGLE_PRIVATE_KEY | No | Service account private key. | |
| GOOGLE_CLIENT_EMAIL | No | Service account client email. | |
| GOOGLE_CLOUD_PROJECT | No | Google Cloud project ID. If not set, inferred from credentials. | |
| GOOGLE_APPLICATION_CREDENTIALS | No | Path to the service account key file. |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| gcp-logging-query-logsB | Query Google Cloud Logs with custom filters. Searches across all payload types (text, JSON, proto) and metadata fields. |
| gcp-logging-query-time-rangeA | Query Google Cloud Logs within a specific time range. Supports relative times (1h, 2d) and ISO timestamps. |
| gcp-logging-search-comprehensiveC | Search across all log fields including textPayload, jsonPayload, protoPayload, labels, HTTP requests, and metadata. Provides maximum context. |
| gcp-spanner-execute-queryD | – |
| gcp-spanner-list-tablesD | – |
| gcp-spanner-list-instancesD | – |
| gcp-spanner-list-databasesD | – |
| gcp-spanner-query-natural-languageD | – |
| gcp-spanner-query-countD | – |
| gcp-monitoring-query-metricsD | – |
| gcp-monitoring-list-metric-typesD | – |
| gcp-monitoring-query-natural-languageD | – |
| gcp-trace-get-traceD | – |
| gcp-trace-list-tracesD | – |
| gcp-trace-find-from-logsD | – |
| gcp-trace-query-natural-languageD | – |
| gcp-iam-get-project-policyB | Retrieve the IAM policy for a Google Cloud project |
| gcp-iam-test-project-permissionsA | Test which permissions the current caller has on a Google Cloud project |
| gcp-iam-test-resource-permissionsA | Test which permissions the current caller has on specific Google Cloud resources |
| gcp-iam-validate-deployment-permissionsA | Check if current caller has required permissions for deploying to common GCP services |
| gcp-iam-list-deployment-servicesB | List all GCP services with pre-defined deployment permission sets |
| gcp-iam-analyse-permission-gapsC | Compare current permissions against required permissions for specific operations and identify gaps |
| gcp-error-reporting-list-groupsD | – |
| gcp-error-reporting-get-group-detailsD | – |
| gcp-error-reporting-analyse-trendsD | – |
| gcp-profiler-list-profilesD | – |
| gcp-profiler-analyse-performanceD | – |
| gcp-profiler-compare-trendsD | – |
| gcp-billing-list-accountsA | List all Google Cloud billing accounts accessible to the user |
| gcp-billing-get-account-detailsA | Retrieve detailed information about a specific Google Cloud billing account |
| gcp-billing-list-projectsA | List all projects associated with a specific Google Cloud billing account |
| gcp-billing-get-project-infoA | Retrieve billing configuration and status for a Google Cloud project |
| gcp-billing-list-servicesB | List all available Google Cloud services for billing and cost analysis |
| gcp-billing-list-skusB | List all SKUs (Stock Keeping Units) and pricing information for a Google Cloud service |
| gcp-billing-analyse-costsC | Perform detailed cost analysis with trends and insights for Google Cloud billing data |
| gcp-billing-detect-anomaliesC | Detect unusual cost patterns and spending anomalies in Google Cloud billing data |
| gcp-billing-cost-recommendationsB | Generate cost optimisation recommendations with potential savings for Google Cloud billing |
| gcp-billing-service-breakdownC | Get detailed cost breakdown by Google Cloud service with usage and SKU information |
| gcp-compute-list-instancesA | List Compute Engine VM instances across the project or within a zone |
| gcp-compute-delete-instanceA | Delete a Compute Engine VM instance by name and zone |
| gcp-compute-create-instanceA | Create a Compute Engine VM instance with simple parameters |
| gcp-compute-get-instance-ipB | Fetch external IP(s) for a VM and provide suggested SSH commands |
| gcp-compute-start-instanceB | Start a stopped Compute Engine VM instance |
| gcp-compute-stop-instanceB | Stop a running Compute Engine VM instance |
| deploy-static-html-siteB | Create a VM with a startup script that installs nginx and writes provided HTML to /var/www/html/index.html |
| get-compute-vm-statusB | Retrieve the status of a Compute Engine VM instance |
| get-compute-vm-ipB | Fetch the external IP of a VM and return an http URL |
| create-static-site-bucketB | Create a Cloud Storage bucket configured for static site hosting (uniform bucket-level access). |
| upload-static-site-htmlB | Upload an HTML file to Cloud Storage and make it publicly readable. |
| list-static-site-bucketsB | List Cloud Storage buckets in the project. |
| delete-static-site-bucketA | Delete a Cloud Storage bucket (must be empty). |
| deploy-static-site-from-htmlB | Create a bucket, upload HTML, and provision a VM that serves the bucket content via nginx. |
| gcp-list-project-idsB | List all accessible Google Cloud project IDs |
| generate_gcp_mermaid_diagramA | Generate a Mermaid architecture diagram for a GCP project |
| gcp-utils-set-project-idB | Set the default Google Cloud project ID to use for all operations |
| gcp-utils-get-project-idA | Get the current Google Cloud project ID and recent project history |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| analyse-errors | Analyse errors in logs over a specified timeframe with optional severity and service filtering |
| trace-request | Trace a specific request through logs using trace ID |
| performance-overview | Get a performance overview for services over a specified timeframe |
| alert-investigation | Investigate a specific alert and analyse related metrics and logs |
| schema-explanation | Get a comprehensive overview of a Cloud Spanner database schema |
| query-optimisation | Analyse and provide optimisation suggestions for a Cloud Spanner SQL query |
| data-exploration | Analyse a Cloud Spanner table schema, performance, and data patterns |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 56 tools
Multiple tools appear to do the same thing: gcp-compute-get-instance-ip vs get-compute-vm-ip, gcp-logging-query-logs vs gcp-logging-search-comprehensive, deploy-static-html-site vs deploy-static-site-from-html, plus several natural-language query variants for Spanner, Monitoring, and Trace. Many tools have no descriptions at all, making boundaries impossible to distinguish reliably.
Most tools follow a readable gcp-service-verb-noun pattern, which helps navigation. However, the pattern is broken by unprefixed tools like deploy-static-html-site and get-compute-vm-ip, and by generate_gcp_mermaid_diagram using underscores. These are mixed conventions rather than complete chaos.
56 tools is well above the 25+ threshold for a coherent toolkit. The count feels bloated because several tools could be consolidated, such as IP retrieval, logging queries, static-site deployment, and cost analysis variants.
The server covers a broad read-only observability and billing surface, plus basic compute and static-site workflows, but major GCP services like BigQuery, Cloud Run, GKE, and full Cloud Storage are missing. Even within covered services there are notable gaps: no IAM policy updates, no Spanner writes/DDL, no compute update, and no object-level static-site deletion.