ui_type
Type text into the currently focused field using simulated keystrokes via System Events. Optionally activate a specific app first. Requires Accessibility permissions.
This record as markdown: /tools/heznpc-airmcp/ui-type.md
What ui_type does on AirMCP
AI agents invoke ui_type 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 ui_type is rated High
This tool simulates keyboard input into whatever field currently has focus, which is an external operation whose effects entirely depend on context and arguments. It can type into any application — including terminal, password fields, forms, or chat — making it high severity since an AI agent could inject arbitrary text into sensitive or dangerous contexts.
From the tool's definition 'Type text into the currently focused field using simulated keystrokes via System Events' — this triggers external OS-level input simulation via accessibility APIs
Attacks that exploit this kind of access
The rule that runs ui_type 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 ui_type, this is the rule to start with:
ui_type 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 ui_type call is checked against it from then on.
Questions about ui_type
Type text into the currently focused field using simulated keystrokes via System Events. Optionally activate a specific app first. Requires Accessibility permissions. 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 ui_type: 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.
ui_type 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 ui_type 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 ui_type. 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.
ui_type 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