Create a new option set
AI agents use create_option_set to create or update resources in HAP MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your HAP MCP Server environment.
This tool creates a new option set, which is a write operation that modifies system configuration/metadata. While it creates new data, this is reversible (consistent with sibling tool 'delete_option_set' existing on the same server), and does not irreversibly destroy data, execute arbitrary code, or move money.
From the tool's definition Tool name 'create_option_set' and description 'Create a new option set' indicate data creation. The action is reversible (option sets can typically be deleted), and the blast radius is limited to configuration/metadata management rather than core business…
Attacks that exploit this kind of access
Create a new option set. It is categorised as a Write tool in the HAP MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the HAP MCP Server MCP server in PolicyLayer and add a rule for create_option_set: 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 HAP MCP Server. Nothing to install.
create_option_set is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_option_set 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 create_option_set. 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.
create_option_set is provided by the HAP MCP Server MCP server (mingdaocloud/hap-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 →