AI agents call describe_stack_events to retrieve information from Sceptre without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical event data from a CloudFormation stack. The describe_* pattern on this server (alongside describe_change_set, describe_stack, describe_stack_outputs, describe_stack_resources) consistently indicates read-only query operations. Retrieving stack events has no side effects, does not modify state, and poses minimal security risk even if misused by an AI agent.
From the tool's definition Tool name contains 'describe' and description explicitly states 'Retrieve the events' with no mention of modifications, deletions, or side effects.
Attacks that exploit this kind of access
Retrieve the events for a CloudFormation stack via Sceptre. It is categorised as a Read tool in the Sceptre MCP Server, which means it retrieves data without modifying state.
Register the Sceptre MCP server in PolicyLayer and add a rule for describe_stack_events: 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.
describe_stack_events is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the describe_stack_events 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 describe_stack_events. 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.
describe_stack_events 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →