AI agents call diff_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 'diff' operation typically returns a comparison of two states without modifying infrastructure. While the description is empty (lowering confidence), the name strongly implies a read-only query operation similar to other describe_* tools on the server.
From the tool's definition Tool name 'diff_stack' suggests a comparison or read operation that shows differences between stack states.
Attacks that exploit this kind of access
diff_stack. 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 diff_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.
diff_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 diff_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 diff_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.
diff_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 →