Design a pyramidal horn antenna for specified gain. Calculates aperture dimensions and length.
AI agents use openems_create_horn to create or update resources in Mcp Openems — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Openems environment.
This tool generates/creates a horn antenna design with calculated dimensions. It produces a new design structure (Write), with no code execution, deletion, or financial implications. Severity is low since it only creates a local design object within the simulation environment.
From the tool's definition 'Design a pyramidal horn antenna' and 'Calculates aperture dimensions and length' — creates a new antenna design artifact
Attacks that exploit this kind of access
Design a pyramidal horn antenna for specified gain. Calculates aperture dimensions and length. It is categorised as a Write tool in the Mcp Openems MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Openems MCP server in PolicyLayer and add a rule for openems_create_horn: 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 Mcp Openems. Nothing to install.
openems_create_horn 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 openems_create_horn 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 openems_create_horn. 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.
openems_create_horn is provided by the Mcp Openems MCP server (rfingadam/mcp-openems). 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 →