This record as markdown: /tools/heznpc-airmcp/generate-structured.md
What generate_structured does on AirMCP
AI agents invoke generate_structured to trigger actions in AirMCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why generate_structured is rated High
The tool appears to invoke an Apple AI/Intelligence feature to generate structured JSON output. This is an execution of an AI model or system call. The description is incomplete ('from Apple' is truncated), which lowers confidence. Given sibling tools like 'ai_agent', 'ai_chat', and 'ai_plan_metrics', this likely triggers an AI inference operation.
From the tool's definition 'Generate structured JSON output from Apple' — description is vague and truncated, referencing Apple Intelligence or similar AI generation capability
Attacks that exploit this kind of access
The rule that runs generate_structured safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AirMCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For generate_structured, this is the rule to start with:
generate_structured stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect AirMCP, apply this rule, and every generate_structured call is checked against it from then on.
Questions about generate_structured
Generate structured JSON output from Apple. It is categorised as a Execute tool in the AirMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Air MCP server in PolicyLayer and add a rule for generate_structured: 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 AirMCP. Nothing to install.
generate_structured is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the generate_structured 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 generate_structured. 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.
generate_structured is provided by the Air MCP server (airmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Air, and thousands of servers like it.
This server
Across the catalogue