AI agents call list_stacks 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.
The tool name 'list_stacks' strongly indicates a data retrieval operation that queries existing CloudFormation stacks without side effects. Despite the empty description, the naming pattern and server context (Sceptre is a CloudFormation orchestration tool) confirm this is a read-only enumeration tool. Confidence is high due to unambiguous naming conventions.
From the tool's definition Tool name 'list_stacks' follows read-pattern naming conventions (list/get/fetch). No description provided, but context from sibling tools (describe_*, delete_*, create_*) and the Sceptre CloudFormation management purpose establish this as a query operation.
Attacks that exploit this kind of access
list_stacks. 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 list_stacks: 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.
list_stacks 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 list_stacks 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 list_stacks. 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.
list_stacks 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 →