cloud_security
Cloud: environment detection, metadata audit, IAM credentials, storage audit, IMDS security
This record as markdown: /tools/defense/cloud-security.md
What cloud_security does on Defense
AI agents call cloud_security to retrieve information from Defense without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
action | string | Yes | Cloud security action |
provider | string | — | Cloud provider to target |
output_format | string | — | Output format |
Parameters from the server's own tool schema.
Why cloud_security is rated Low
The described actions — environment detection, metadata auditing, IAM credential inspection, storage auditing, and IMDS security checks — are primarily read/query operations that retrieve and assess cloud configuration data. However, 'IMDS security' could imply hardening actions (writes), and access to IAM credentials represents a sensitive read with a meaningful blast radius if misused (credential exposure).
From the tool's definition environment detection, metadata audit, IAM credentials, storage audit, IMDS security
Attacks that exploit this kind of access
The rule that runs cloud_security safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Defense, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cloud_security, this is the rule to start with:
cloud_security is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Defense, apply this rule, and every cloud_security call is checked against it from then on.
Questions about cloud_security
Cloud: environment detection, metadata audit, IAM credentials, storage audit, IMDS security. It is categorised as a Read tool in the Defense MCP Server, which means it retrieves data without modifying state.
cloud_security accepts 3 parameters: action, provider, output_format. Required: action. The full parameter table on this page comes from the server's own tool schema.
Register the Defense MCP server in PolicyLayer and add a rule for cloud_security: 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 Defense. Nothing to install.
cloud_security 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 cloud_security 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 cloud_security. 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.
cloud_security is provided by the Defense MCP server (defense-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Defense, and thousands of servers like it.
This server
Across the catalogue