Create a new serverless inference subscription.
AI agents use create_serverless_inference 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.
This tool creates a new resource (serverless inference subscription) in Vultr cloud, which is a reversible write operation. It may incur costs but does not directly move money or commit financial obligations — it provisions a subscription that could be deleted. Severity is medium due to potential unexpected cost implications of spinning up cloud resources.
From the tool's definition Create a new serverless inference subscription
Documented attack patterns abuse exactly the kind of access create_serverless_inference gives an agent:
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_serverless_inference:
{
"version": "1",
"default": "deny",
"tools": {
"create_serverless_inference": {
"limits": [
{
"counter": "create_serverless_inference_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_serverless_inference 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.
Free to start. No card required.
Create a new serverless inference subscription. 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.
Register the Vultr MCP server in PolicyLayer and add a rule for create_serverless_inference: 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.
create_serverless_inference is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_serverless_inference 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.
Set action: deny in the PolicyLayer policy for create_serverless_inference. 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.
create_serverless_inference 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.
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.