AI agents use create_service to create or update resources in Render — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Render environment.
Creating a new service on Render is a reversible write operation—services can be deleted or modified after creation. However, it has elevated severity (high, not medium) because: (1) it may trigger automatic deployments with associated compute costs, (2) it allocates platform resources, and (3) misuse by an agent could rapidly spawn multiple services.
From the tool's definition Tool name 'create_service' and description 'Create a new service' indicate data creation. In context of Render deployment platform, this creates new service resources that can incur costs and consume platform resources.
Documented attack patterns abuse exactly the kind of access create_service gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Render, and nothing reaches the server without passing your rules. This is the rule we recommend for create_service:
{
"version": "1",
"default": "deny",
"tools": {
"create_service": {
"limits": [
{
"counter": "create_service_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_service 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 service. It is categorised as a Write tool in the Render MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Render MCP server in PolicyLayer and add a rule for create_service: 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 Render. Nothing to install.
create_service 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_service 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_service. 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_service is provided by the Render MCP server (niyogi/render-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Render, 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.
8 Render tools catalogued and risk-classified — across an index of 43,000+ MCP servers.