Medium Risk

create_read_replica

create_read_replica

How to control create_read_replica ↓

What create_read_replica does on Vultr MCP

AI agents use create_read_replica to create or update resources in Vultr MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vultr MCP environment.

Medium Risk

Why create_read_replica needs a policy

This tool creates a new database read replica, which is a reversible modification operation. While it provisions infrastructure, replicas can be deleted and do not permanently destroy data. The primary impact is resource creation (Write category). Severity is high because creating cloud resources can incur costs and affects system architecture, but the operation is reversible.

From the tool's definition Tool name 'create_read_replica' indicates creation of a database read replica resource. The 'create_' prefix is characteristic of Write operations that instantiate new cloud infrastructure.

Documented attack patterns abuse exactly the kind of access create_read_replica gives an agent:

How to control create_read_replica

PolicyLayer is an MCP gateway — it sits between your AI agents and Vultr MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for create_read_replica:

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

create_read_replica stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Vultr MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about create_read_replica

What does the create_read_replica tool do? +

create_read_replica. It is categorised as a Write tool in the Vultr 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_read_replica? +

Register the Vultr MCP server in PolicyLayer and add a rule for create_read_replica: 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 Vultr MCP. Nothing to install.

What risk level is create_read_replica? +

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

Can I rate-limit create_read_replica? +

Yes. Add a rate_limit block to the create_read_replica 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_read_replica completely? +

Set action: deny in the PolicyLayer policy for create_read_replica. 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_read_replica? +

create_read_replica is provided by the Vultr MCP server (rsp2k/mcp-vultr). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Vultr MCP tool call.

Start from Vultr MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

284 Vultr MCP 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.