// SCAN REPORT

Mcp

23 tools. 8 can modify or destroy data without limits.

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

Last updated: 15 Sept 2026

8 can modify or destroy data

15 read-only

23 tools total

Community server · catalogue entry checked 15/09/2026 · full schemas captured for 23 of 23 tools

How to control Mcp ↓

TOOL MAP

What Mcp exposes to your agents

Read (15) Write / Execute (7) 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_k8s_resource This tool permanently removes Kubernetes resources (pods, deployments, services, etc.) from a cluster with no built-in undo mechanism. Execute · Medium cancel_operation Cancelling a GKE operation is an external action that interrupts an in-progress process (e.g., cluster creation, upgrade, resize). Write · High apply_k8s_manifest Applying a Kubernetes manifest creates or modifies resources in a cluster (deployments, services, configs, RBAC rules, etc.). Write · High create_cluster This tool provisions a new GKE cluster, which is a significant Write operation.

8 of Mcp's 23 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_k8s_resource": {
    "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

{
  "apply_k8s_manifest": {
    "limits": [
      {
        "counter": "apply_k8s_manifest_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_k8s_auth": {
    "limits": [
      {
        "counter": "check_k8s_auth_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 23 Mcp tools

DESTRUCTIVE 1 tools

Destructive delete_k8s_resource Deletes a Kubernetes resource from a cluster. This is similar to running kubectl delete.

EXECUTE 1 tools

Execute cancel_operation Cancels a specific GKE operation.

WRITE 6 tools

Write apply_k8s_manifest Applies a Kubernetes manifest to a cluster using server-side apply. This is similar to running kubectl apply - Write create_cluster Creates a new GKE cluster in a given project and location. It's recommended to read the [GKE documentation](ht Write create_node_pool Creates a node pool for a specific GKE cluster. Write patch_k8s_resource Patches a Kubernetes resource. This is similar to running kubectl patch. Write update_cluster Updates a specific GKE cluster. Write update_node_pool Updates a specific node pool within a GKE cluster.

READ 15 tools

Read check_k8s_auth Checks whether an action is allowed on a Kubernetes resource. This is similar to running kubectl auth can-i. Read describe_k8s_resource Shows the details of a specific Kubernetes resource. This is similar to running kubectl describe. Read get_cluster Gets the details of a specific GKE cluster. Read get_k8s_cluster_info Gets cluster endpoint information. This is similar to running kubectl cluster-info. Read get_k8s_logs Gets logs from a Kubernetes container in a pod. This is similar to running kubectl logs. Read get_k8s_resource Gets one or more Kubernetes resources from a cluster. Resources can be filtered by type, name, namespace, and Read get_k8s_rollout_status Checks the current rollout status of a Kubernetes resource. This is similar to running kubectl rollout status. Read get_k8s_version Retrieves Kubernetes client and server versions for a given cluster. This is similar to running kubectl versio Read get_node_pool Gets the details of a specific node pool within a GKE cluster. Read get_operation Gets the details of a specific GKE operation. Read list_clusters Lists GKE clusters in a given project and location. Location can be a region, zone, or '-' for all locations. Read list_k8s_api_resources Retrieves the available API groups and resources from a Kubernetes cluster. This is similar to running kubectl Read list_k8s_events Retrieves events from a Kubernetes cluster. This is similar to running kubectl events. Read list_node_pools Lists the node pools for a specific GKE cluster. Read list_operations Lists GKE operations in a given project and location. Location can be a region, zone, or '-' for all locations

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_k8s_resource. 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 6 write tools including apply_k8s_manifest, create_cluster, create_node_pool. 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? +

23 tools across 3 categories: Destructive, Read, Write. 15 are read-only. 8 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 23 Mcp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP →

Instant setup, no code required.

23 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 →