AI agents call CloudFormation to retrieve information from Aws Claw without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries CloudFormation stack metadata and state without modifying, deleting, or executing anything. It has no side effects and presents only informational operations. Severity is low because the blast radius of exposing stack visibility to an agent is minimal—no resources are created, altered, or destroyed.
From the tool's definition Tool description explicitly states: 'list stacks, describe stack resources and events.' All verbs are read-only operations: list, describe.
Attacks that exploit this kind of access
list stacks, describe stack resources and events. It is categorised as a Read tool in the Aws Claw MCP Server, which means it retrieves data without modifying state.
Register the Aws Claw MCP server in PolicyLayer and add a rule for CloudFormation: 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 Aws Claw. Nothing to install.
CloudFormation 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 CloudFormation 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 CloudFormation. 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.
CloudFormation is provided by the Aws Claw MCP server (necatiarslan/awsclaw). 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 →