AI agents call get_action to retrieve information from Hcloud without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves information about an action's state/progress. It has no side effects—it only reads data. While actions themselves may involve infrastructure changes, this tool merely queries the status of already-initiated operations, making it a Read category tool with low severity.
From the tool's definition Tool description states "Get a single action by ID" and "to check progress or status after create/delete". This is a retrieval operation that queries the status of an existing action without modifying or executing anything.
Attacks that exploit this kind of access
Get a single action by ID (e.g. to check progress or status after create/delete). It is categorised as a Read tool in the Hcloud MCP Server, which means it retrieves data without modifying state.
Register the Hcloud MCP server in PolicyLayer and add a rule for get_action: 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 Hcloud. Nothing to install.
get_action 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 get_action 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 get_action. 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.
get_action is provided by the Hcloud MCP server (xodus-co/hcloud-mcp). 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 →