Medium Risk

create_instance

Create a new instance in the specified project. The request requires project_id, instance_id, display_name, and at least one cluster. The instance_id must be RFC 1035 compliant. Each cluster must specify its zone (e.g. us-central1-a). Example: { "project_id": "my-project", "instance_id": "my-inst...

Part of the Mcp server.

create_instance can modify Mcp data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE MCP →

Free to start. No card required.

AI agents use create_instance to create or modify resources in Mcp. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call create_instance repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Mcp.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_instance": {
      "limits": [
        {
          "counter": "create_instance_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Mcp policy for all 13 tools.

Get this rule live on your own Mcp server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY MCP →

View all 13 tools →

These attack patterns abuse exactly the kind of access create_instance gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so create_instance only ever does what you allow.

SECURE MCP →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the create_instance tool do? +

Create a new instance in the specified project. The request requires project_id, instance_id, display_name, and at least one cluster. The instance_id must be RFC 1035 compliant. Each cluster must specify its zone (e.g. us-central1-a). Example: { "project_id": "my-project", "instance_id": "my-instance", "display_name": "This is my instance", "clusters": [ { "zone": "us-central1-a", "serve_nodes": 3, "default_storage_type": "SSD" } ] }. It is categorised as a Write tool in the Mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_instance? +

Register the MCP server in PolicyLayer and add a rule for create_instance: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp. Nothing to install.

What risk level is create_instance? +

create_instance is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_instance? +

Yes. Add a rate_limit block to the create_instance rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block create_instance completely? +

Set action: deny in the PolicyLayer policy for create_instance. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides create_instance? +

create_instance is provided by the MCP server (https://bigtableadmin.googleapis.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp tool call.

Deterministic rules across all 13 Mcp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.