ui_keystroke
Sends a key combination, e.g. "cmd+shift+5", "return", "cmd+,", "escape". Modifiers: cmd, shift, alt/option, ctrl, fn. The last token is the key. unknown_key if the key isn't recognized. Requires Accessibility permission.
This record as markdown: /tools/com-local-mcp-local-mcp/ui-keystroke.md
What ui_keystroke does on Local
AI agents invoke ui_keystroke to trigger actions in Local. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
keys | string | Yes | e.g. cmd+shift+5, return, cmd+, |
Parameters from the server's own tool schema.
Why ui_keystroke is rated High
This tool sends arbitrary keystrokes to the system, which can trigger any action on the user's machine—opening apps, deleting files, submitting forms, or executing commands—depending on the active context. It operates at the OS level via Accessibility APIs, giving it a broad blast radius.
From the tool's definition Sends a key combination... Requires Accessibility permission
Attacks that exploit this kind of access
The rule that runs ui_keystroke safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ui_keystroke, this is the rule to start with:
ui_keystroke 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 Local, apply this rule, and every ui_keystroke call is checked against it from then on.
Questions about ui_keystroke
Sends a key combination, e.g. "cmd+shift+5", "return", "cmd+,", "escape". Modifiers: cmd, shift, alt/option, ctrl, fn. The last token is the key. unknown_key if the key isn't recognized. Requires Accessibility permission. It is categorised as a Execute tool in the Local MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
ui_keystroke accepts 1 parameter: keys. Required: keys. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for ui_keystroke: 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 Local. Nothing to install.
ui_keystroke 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_keystroke 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_keystroke. 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_keystroke is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local, and thousands of servers like it.
Across the catalogue