AI agents call describe_stack 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 performs a read-only query to retrieve and return information about an existing CloudFormation stack. The verb 'describe' combined with 'returning full stack details' confirms this is a data retrieval operation with no capability to modify, delete, or execute changes to infrastructure.
From the tool's definition Tool name 'describe_stack' and description 'Describe a CloudFormation stack via Sceptre, returning full stack details' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Describe a CloudFormation stack via Sceptre, returning full stack details. 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: 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 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 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. 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 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 →