Storage

61 tools. 24 can modify or destroy data without limits.

7 destructive tools with no built-in limits. Policy required.

Last updated:

24 can modify or destroy data
37 read-only
61 tools total

Community server · catalogue entry verified 26/06/2026

How to control Storage ↓

What Storage exposes to your agents

Read (37) Write / Execute (17) Destructive / Financial (7)
Critical Risk

The most dangerous Storage tools

24 of Storage's 61 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Storage

PolicyLayer is an MCP gateway — it sits between your AI agents and Storage, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "delete_backup": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "copy_object": {
    "limits": [
      {
        "counter": "copy_object_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "check_iam_permissions": {
    "limits": [
      {
        "counter": "check_iam_permissions_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Storage — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON STORAGE →

Instant setup, no code required.

All 61 Storage tools

READ 37 tools
Read check_iam_permissions Tests IAM permissions for a bucket. Read download_object Downloads an object from GCS to a local file. Read find_protectable_resources Lists protectable resources in a project. This includes Cloud SQL instances, Compute VMs, and Compute Disks. Read get_backup Gets a backup. Read get_backup_plan Gets a backup plan. Read get_backup_plan_association Gets a backup plan association. Read get_backup_vault Gets a backup vault. Read get_backupdr_operation Gets the status of a BackupDR operation. Read get_bucket_location Gets the location and storage class of a bucket. Read get_bucket_metadata Gets detailed metadata for a specific bucket. Read get_csql_operation Gets the status of a Cloud SQL operation. Read get_datasource Gets a data source. Read get_metadata_table_schema Checks if GCS insights service is enabled and returns the BigQuery table schema for a given insights dataset c Read get_trace Use this as the primary tool to retrieve a single distributed trace from Google Cloud Trace. Traces provid Read list_alert_policies Use this as the primary tool to list the alerting policies in a Google Cloud project. Alerting policies de Read list_alerts Use this as the primary tool to list the alerts in a Google Cloud project. An alert is the representation Read list_backup_plan_associations Lists all backup plan associations for a given backup plan. Read list_backup_plans Lists all backup plans in a given project and location. Read list_backup_vaults Lists all backup vaults in a given project and location. Read list_backups Lists all backups for a given data source in a backup vault. Read list_buckets Use this as the primary tool to list the log buckets in a Google Cloud project. Log buckets are containers Read list_datasources Lists all data sources in a given backup vault. Read list_group_stats Use this tool ONLY to find and analyze recurring stack traces in your application. It aggregates similar Read list_insights_configs Lists the names of all Storage Insights dataset configurations for a given project. Read list_log_entries Use this as the primary tool to search and retrieve log entries from Google Cloud Logging. It Read list_log_names Use this as the primary tool to list the log names in a Google Cloud project. This is useful for discoveri Read list_log_scopes Use this as the primary tool to list the log scopes in a Google Cloud project. Log scopes allow you to que Read list_metric_descriptors Use this as the primary tool to discover the types of metrics available in a Google Cloud project. This is Read list_objects Lists the names of objects in a Google Cloud Storage (GCS) bucket. Supports filtering by prefix, directory-lik Read list_resource_backup_configs Lists all resource backup configs in a given project and location. Read list_sinks Use this as the primary tool to list the log sinks in a Google Cloud project. Log sinks control how Cloud Read list_time_series Use this as the primary tool to retrieve metric data over a specific time period. This is the core tool fo Read list_traces Use this as the primary tool to retrieve and examine distributed traces from Google Cloud Trace. Traces pr Read list_views Use this as the primary tool to list the log views in a given log bucket. Log views provide fine-grained a Read read_object_content Reads the content of a specific object. Read read_object_metadata Reads metadata for a specific object. Read view_iam_policy Views the IAM policy for a bucket.

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Storage

Can an AI agent delete data through the Storage MCP server? +

Yes. The Storage server exposes 7 destructive tools including delete_backup, delete_backup_plan, delete_backup_plan_association. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Storage? +

The Storage server has 15 write tools including copy_object, copy_object_safe, create_backup_plan. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Storage.

How many tools does the Storage MCP server expose? +

61 tools across 4 categories: Destructive, Execute, Read, Write. 37 are read-only. 24 can modify, create, or delete data.

How do I enforce a policy on Storage? +

Register the Storage MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Storage tool call.

Deterministic rules across all 61 Storage tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

61 Storage tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.