AI agents use create_change_set to create or update resources in Sceptre — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sceptre environment.
Creating a CloudFormation change set is a Write operation: it generates a proposed set of changes to a stack but does not execute them. It is reversible (change sets can be deleted without applying). Severity is medium because it modifies CloudFormation state and could be a precursor to destructive infrastructure changes, but by itself does not apply or destroy anything.
From the tool's definition Tool name: 'create_change_set' — in the context of a Sceptre CloudFormation management MCP server, a change set is a preview of proposed infrastructure changes.
Attacks that exploit this kind of access
create_change_set. It is categorised as a Write tool in the Sceptre MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sceptre MCP server in PolicyLayer and add a rule for create_change_set: 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 Sceptre. Nothing to install.
create_change_set 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_change_set 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_change_set. 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_change_set is provided by the Sceptre MCP server (sceptre/sceptre-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
create_change_set is one line of Sceptre's registry record.
The record carries the whole server: 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 →