MCP Vibe Coding Tools
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAG_DOCS_PATH | No | Path to directory containing documents to index for RAG tools. Required for RAG functionality. | |
| WORKSPACE_PATH | No | Path to the workspace directory. If not set, the current working directory is used. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| gcloud_auth_loginA | Authenticate with Google Cloud using Application Default Credentials (ADC). This will open a browser for OAuth flow. |
| gcloud_auth_listA | List all authenticated accounts and show the active account |
| gcloud_auth_print_access_tokenB | Generate and print an access token for the active account. Useful for API calls. |
| gcloud_auth_print_identity_tokenA | Generate and print an identity token (JWT) for the active account. Used for authenticating to Cloud Run and other services. |
| gcloud_config_setC | Set a gcloud configuration property (project, region, zone, etc.) |
| gcloud_config_getC | Get the value of a gcloud configuration property |
| gcloud_config_listA | List all gcloud configuration properties |
| gcloud_logging_readB | Read logs from Cloud Logging with filters and time range |
| gcloud_logging_writeC | Write a log entry to Cloud Logging |
| gcloud_container_clusters_listC | List all GKE clusters in the current project |
| gcloud_container_clusters_describeB | Get detailed information about a specific GKE cluster |
| gcloud_container_clusters_get_credentialsA | Get kubectl credentials for a GKE cluster |
| gcloud_container_node_pools_listC | List node pools in a GKE cluster |
| gcloud_bq_queryB | Execute a BigQuery SQL query |
| gcloud_bq_lsB | List BigQuery datasets or tables |
| gcloud_bq_showB | Show details about a BigQuery dataset or table |
| gcloud_bq_mkC | Create a BigQuery dataset or table |
| gcloud_dataflow_jobs_listB | List Dataflow jobs in the current project |
| gcloud_dataflow_jobs_describeC | Get detailed information about a Dataflow job |
| gcloud_dataflow_jobs_cancelC | Cancel a running Dataflow job |
| gcloud_projects_listB | List all GCP projects accessible to the authenticated user |
| gcloud_projects_describeA | Get detailed information about a specific GCP project |
| gcloud_services_listA | List enabled Google Cloud APIs and services for a project |
| gcloud_services_enableB | Enable a Google Cloud API or service for a project |
| gcloud_compute_instances_listC | List Compute Engine VM instances |
| gcloud_compute_instances_describeB | Get detailed information about a Compute Engine VM instance |
| gcloud_run_services_listC | List Cloud Run services |
| gcloud_run_services_describeC | Get detailed information about a Cloud Run service |
| gcloud_storage_buckets_listC | List Cloud Storage buckets |
| gcloud_storage_lsB | List objects in a Cloud Storage bucket or path |
| gcloud_iam_service_accounts_listB | List IAM service accounts in the current project |
| gcloud_iam_service_accounts_keys_createB | Create a new key for a service account |
| gcloud_executeA | Execute any gcloud command directly. This is a flexible wrapper that allows running any gcloud command with proper ADC authentication. Use this for commands not covered by specific tools. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 33 tools
Each tool targets a specific GCP resource and action (e.g., gcloud_auth_login vs gcloud_auth_print_access_token), and even similar-looking tools like gcloud_storage_buckets_list vs gcloud_storage_ls are clearly distinct (buckets vs objects). The catch-all gcloud_execute is explicitly for commands not covered, so it doesn't cause ambiguity.
All tools follow a strict pattern: 'gcloud_<service>_<resource>_<verb>' (e.g., gcloud_container_clusters_list, gcloud_bq_query). The naming is uniform with consistent snake_case and predictable hierarchy, making it easy for an agent to infer function from name.
With 33 tools, the set is fairly large for an MCP server. While each tool targets a distinct GCP operation, the scope feels broad—covering many services but not deeply. The count exceeds the typical well-scoped range (3-15), but the consistent naming and organization mitigate confusion. It's borderline too heavy.
The tool set provides good coverage for listing and describing resources across several services, but many fundamental lifecycle operations are missing: no create/delete for Cloud Storage buckets, no update/delete for BigQuery, no create for Dataflow or Compute instances. The presence of gcloud_execute can fill gaps but at the cost of consistency and type safety.