AI agents call drift_detect 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.
Drift detection is a read-only operation that queries the current state of a CloudFormation stack and compares it against the template, reporting differences without making any changes. This aligns with the Read category (retrieves or queries data; no side effects). The severity is low because the worst outcome of misuse is exposing information about stack state, not causing infrastructure damage or data loss.
From the tool's definition Tool name 'drift_detect' and description 'Detect configuration drift on a deployed CloudFormation stack via Sceptre' indicates a detection/inspection operation with no modification of resources.
Attacks that exploit this kind of access
Detect configuration drift on a deployed 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 drift_detect: 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.
drift_detect 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 drift_detect 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 drift_detect. 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.
drift_detect 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 →