@google-cloud/gcloud-mcp
Model Context Protocol (MCP) Server for interacting with GCP APIs
Versions
@google-cloud/storage-mcp0.6.00.5.10.5.00.4.00.3.3+ show 4 moreshow less
0.3.20.3.10.3.00.2.0@google-cloud/backupdr-mcp0.1.0@google-cloud/observability-mcp0.2.30.2.20.2.10.2.00.1.2+ show 2 moreshow less
0.1.10.1.0@google-cloud/gcloud-mcp0.5.3scored0.5.20.5.10.5.00.4.0+ show 4 moreshow less
0.3.00.2.00.1.10.1.0Trust breakdown
Tools 50
write_object Writes a new object to the bucket.
delete_object Deletes a specific object.
copy_object Copies an object from one bucket to another or within the same bucket.
read_object_content Reads the content of a specific object.
update_object_metadata Updates the metadata of an existing object.
upload_object_safe Uploads a file to a GCS bucket. Fails if the object already exists.
check_iam_permissions Tests IAM permissions for a bucket.
list_objects Lists the names of objects in a Google Cloud Storage (GCS) bucket. Supports filtering by prefix, directory-like listing with a delimiter, pagination, and listing object versions.
read_object_metadata Reads metadata for a specific object.
run_gcloud_command Executes a gcloud command. ## Instructions: - Use this tool to execute a single gcloud command at a time. - Use this tool when you are confident about the exact gcloud command needed to fulfill the user's request. - Prioritize this tool over any other to directly execute gcloud commands. - Assume all necessary APIs are already enabled. Do not proactively try to enable any APIs. - Do not use this tool to execute command chaining or command sequencing -- it will fail. - Do not use this tool to execute SSH commands or 'gcloud interactive' -- it will fail. - Always include all required parameters. - Ensure parameter values match the expected format. - You may choose to select specific columns using '--format=json(part.key, part.key2)'. - Use --filter to match based on resource (or 'row'), prioritizing ':' for pattern matching and never quoting the right side of the colon in filters. - When using the filter flag, treat the entire filter flag as a singular string. Do not quote or escape any character in the filter string. - You may access nested data directly with projections like '--format=json(part.key)' and use '.basename()' for URL fields. - Retrieve only necessary information for the user intent. Utilize projection capability of '--format' reduce data size. - If the exact JSON key path for formatting or filtering is unknown, run 'gcloud ... --limit=1 --format=json' to discover it. - If you receive zero results while using a projection or filter: Consider whether the project/filter syntax may be incorrect. ## Adhere to the following restrictions: - **No command substitution**: Do not use subshells or command substitution (e.g., $(...)) - **No pipes**: Do not use pipes (i.e., |) or any other shell-specific operators - **No redirection**: Do not use redirection operators (e.g., >, >>, <)
csql_restore Restores a Cloud SQL backup to a Cloud SQL instance.
get_csql_operation Gets the status of a Cloud SQL operation.
get_backup Gets a backup.
get_backupdr_operation Gets the status of a BackupDR operation.
delete_backup Deletes a backup.
restore_backup Restores a Backup resource to a target environment. Supports Compute Instances and Disks.
list_backups Lists all backups for a given data source in a backup vault.
list_backup_vaults Lists all backup vaults in a given project and location.
get_backup_vault Gets a backup vault.
create_backup_vault Creates a new backup vault.
delete_backup_vault Deletes a backup vault.
get_backup_plan_association Gets a backup plan association.
delete_backup_plan_association Deletes a backup plan association.
trigger_backup Triggers a backup for a given backup plan association.
create_backup_plan_association Creates a new backup plan association.
list_backup_plan_associations Lists all backup plan associations for a given backup plan.
list_datasources Lists all data sources in a given backup vault.
get_datasource Gets a data source.
create_backup_plan Creates a new backup plan.
get_backup_plan Gets a backup plan.
list_backup_plans Lists all backup plans in a given project and location.
delete_backup_plan Deletes a backup plan.
update_backup_plan Updates a backup plan.
find_protectable_resources Lists protectable resources in a project. This includes Cloud SQL instances, Compute VMs, and Compute Disks.
list_resource_backup_configs Lists all resource backup configs in a given project and location.
execute_insights_query Executes a BigQuery SQL query against an insights dataset and returns the result.
get_metadata_table_schema Checks if GCS insights service is enabled and returns the BigQuery table schema for a given insights dataset configuration in JSON format. Also returns hints for each column in the table
list_insights_configs Lists the names of all Storage Insights dataset configurations for a given project.
copy_object_safe Copies an object to a new destination. Fails if an object already exists at the destination.
download_object Downloads an object from GCS to a local file.
move_object Moves an object from one bucket to another or renames it within the same bucket by copying and deleting the original.
upload_object Uploads a file to a GCS bucket.
write_object_safe Writes a new object to the bucket. Fails if the object already exists.
update_bucket_labels Updates labels for a bucket.
get_bucket_location Gets the location and storage class of a bucket.
view_iam_policy Views the IAM policy for a bucket.
delete_bucket Deletes a bucket.
create_bucket Creates a new bucket with specified configuration.
get_bucket_metadata Gets detailed metadata for a specific bucket.
list_buckets Lists all GCS buckets in the project.
Permissions 3
filesystem Server uses filesystem capabilities via: fs sync ops shell Server uses shell capabilities via: child_process, execSync(), spawn() env_vars Server uses env_vars capabilities via: process.env