// SCAN REPORT

Mcp

29 tools. 6 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 17 Aug 2026

6 can modify or destroy data

23 read-only

29 tools total

Community server · catalogue entry checked 17/08/2026 · full schemas captured for 29 of 29 tools

How to control Mcp ↓

TOOL MAP

What Mcp exposes to your agents

Read (23) Write / Execute (5) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Mcp tools

Destructive · Critical delete_instance Deleting a VM instance is an irreversible destructive action that terminates compute resources and potentially causes service outages. Execute · High reset_instance Resetting a VM instance forces a hard reboot of a running virtual machine — it is an operational action that triggers an external infrastructure operation. Execute · High start_instance The tool executes an action (starting a VM instance) on external infrastructure. Execute · High stop_instance Stopping a VM instance is an executable action that triggers an external operation on cloud infrastructure.

6 of Mcp's 29 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mcp

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

Deny destructive operations

{
  "delete_instance": {
    "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

{
  "create_instance": {
    "limits": [
      {
        "counter": "create_instance_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_commitment_basic_info": {
    "limits": [
      {
        "counter": "get_commitment_basic_info_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

Create a free account and register Mcp — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP →

Instant setup, no code required.

FULL CATALOGUE

All 29 Mcp tools

DESTRUCTIVE 1 tools

Destructive delete_instance Delete a Google Compute Engine virtual machine (VM) instance. Requires project, zone, and instance name as inp

EXECUTE 3 tools

Execute reset_instance Resets a Google Compute Engine virtual machine (VM) instance. Requires project, zone, and instance name as inp Execute start_instance Starts a Google Compute Engine virtual machine (VM) instance. Requires project, zone, and instance name as inp Execute stop_instance Stops a Google Compute Engine virtual machine (VM) instance. Requires project, zone, and instance name as inpu

WRITE 2 tools

Write create_instance Create a new Google Compute Engine virtual machine (VM) instance. Requires project, zone, and instance name as Write set_instance_machine_type Sets the machine type for a stopped Google Compute Engine instance to the specified machine type. Requires pro

READ 23 tools

Read get_commitment_basic_info Get basic information about a Compute Engine Commitment, including its name, ID, status, plan, type, resources Read get_disk_basic_info Get basic information about a Compute Engine disk, including its name, ID, description, creation timestamp, si Read get_disk_performance_config Get performance configuration of a Compute Engine disk, including its type, size, provisioned IOPS, provisione Read get_instance_basic_info Get basic information about a Compute Engine VM instance, including its name, ID, status, machine type, creati Read get_instance_group_manager_basic_info Get basic information about a Compute Engine managed instance group (MIG), including its name, ID, instance te Read get_instance_template_basic_info Get basic information about a Compute Engine instance template, including its name, ID, description, machine t Read get_instance_template_properties Get instance properties of a Compute Engine instance template. This includes properties such as description, t Read get_reservation_basic_info Get Compute Engine reservation basic info including name, ID, creation timestamp, zone, status, specific reser Read get_reservation_details Get Compute Engine reservation details. Returns reservation details including name, ID, status, creation times Read get_zone_operation Get details of a zone operation, including its id, name, status, creation timestamp, error, warning, HTTP erro Read list_accelerator_types Lists the available Google Compute Engine accelerator types. Requires project and zone as input. Returns accel Read list_commitment_reservations Lists reservations for a Compute Engine Commitment. Returns reservation details including name, ID, status, cr Read list_commitments Lists Compute Engine Commitments in a region. Details for each commitment include name, ID, status, plan, type Read list_disks Lists Compute Engine disks. Details for each disk include name, ID, description, creation timestamp, size, typ Read list_images Lists Compute Engine Images. Details for each image include name, ID, status, family, and creation timestamp. Read list_instance_attached_disks Lists the disks attached to a Compute Engine virtual machine (VM) instance. For each attached disk, the respon Read list_instance_group_managers Lists Compute Engine managed instance groups (MIGs). Details for each MIG include name, ID, instance template, Read list_instance_templates Lists Compute Engine instance templates. Details for each instance template include name, ID, description, mac Read list_instances Lists Compute Engine virtual machine (VM) instances. Details for each instance include name, ID, status, machi Read list_machine_types Lists the available Google Compute Engine machine types. Requires project and zone as input. Returns machine t Read list_managed_instances Lists managed instances for a given managed instance group (MIG). For each instance, details include id, insta Read list_reservations Lists Compute Engine reservations. Details for each reservation include name, ID, creation timestamp, zone, st Read list_snapshots Lists snapshots in a project providing basic information per snapshot including name, id, status, creation tim

EXPLORE

Related servers

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

FAQ

Questions about Mcp

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

Yes. The Mcp server exposes 1 destructive tools including delete_instance. 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 Mcp? +

The Mcp server has 2 write tools including create_instance, set_instance_machine_type. 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 Mcp.

How many tools does the MCP server expose? +

29 tools across 4 categories: Destructive, Execute, Read, Write. 23 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Mcp? +

Register the 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 Mcp tool call.

Deterministic rules across all 29 Mcp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP →

Instant setup, no code required.

29 Mcp tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from 's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →