Skip to main content
Glama

NoMac

by app.nomac
OverviewDiscussionsAdmin

Type and click on a Mac

mac_input
Destructive

Sends real keyboard and mouse input, as a person at the Mac would, also on the lock screen and in password dialogs. action: type (text), key (keys such as return or cmd+q), click, move or scroll (x, y), password (types the login password into the focused field), unlock (a locked screen) or size. Answers with a screenshot unless screenshot is false. A retry types again.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNoFor click, move and scroll: from the left, as in screenshot_mac's image (1440 wide).
yNoFor click, move and scroll: from the top, as in screenshot_mac's image (900 high).
keysNoFor key: names or combinations, pressed in order, like ["cmd+a", "backspace"]
textNoFor type: up to 500 characters; for longer text, pbcopy it with exec_mac, then key cmd+v
stepsNoFor scroll: negative up, positive down
actionYestype, key, click, move, scroll, password (types the Mac's login password), unlock (opens a locked screen) or size.
buttonNoFor click: left (default) or right.
doubleNoFor click: true for a double click.
screenshotNofalse skips the screenshot taken after the input (default true).
session_idNoMac session ID (ses_…). Optional: without it, the account's running Mac.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / x / description
      Previous value: -"For click, move and scroll: points from the left edge, as in screenshot_mac's image (1440 wide)."New value: +"For click, move and scroll: from the left, as in screenshot_mac's image (1440 wide)."
    • changedInput schema / properties / y / description
      Previous value: -"For click, move and scroll: points from the top edge, as in screenshot_mac's image (900 high)."New value: +"For click, move and scroll: from the top, as in screenshot_mac's image (900 high)."
  2. Changed2 schema fields changed
    • changedInput schema / properties / session_id / description
      Previous value: -"Mac session ID (ses_…) returned by start_mac or list_mac_sessions."New value: +"Mac session ID (ses_…). Optional: without it, the account's running Mac."
    • changedInput schema / required
      Previous value: -[
-  "session_id",
-  "action"
-]New value: +[
+  "action"
+]
  3. Changed2 schema fields changed
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • changedOutput schema / (root)
      Previous value: -{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "additionalProperties": {},
-  "description": "The JSON response of the NoMac API for this operation",
-  "properties": {
-    "error": {
-      "additionalProperties": {},
-      "description": "Present only when the call failed",
-      "properties": {
-        "code": {
-          "description": "Stable machine-readable error code, for example insufficient_credit",
-          "type": "string"
-        },
-        "message": {
-          "description": "What went wrong and what to do next",
-          "type": "string"
-        }
-      },
-      "required": [
-        "code",
-        "message"
-      ],
-      "type": "object"
-    }
-  },
-  "type": "object"
-}New value: +null
  4. Added

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructive=true, openWorld=true and non-idempotent, so the safety profile is covered. The description adds genuinely non-redundant traits: it operates on the lock screen and in password dialogs, it returns a screenshot unless suppressed, and 'a retry types again' warns that repeating the call duplicates input rather than being idempotent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two front-loaded sentences that state capability, then action-to-parameter mapping, with zero filler. The action list is dense but each item earns its place by mapping an enum value to its parameter.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description compensates by stating that the call answers with a screenshot unless screenshot=false. For a 10-parameter, open-world GUI automation tool the coverage is solid, though coordinate scaling and session defaulting are left to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the baseline is 3, and the description largely restates what the schema already documents (action meanings, screenshot toggling, x/y coordinate reference). It adds no syntax or format detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

It names a specific verb and resource ('Sends real keyboard and mouse input, as a person at the Mac would') and immediately scopes the capability to the lock screen and password dialogs, which separates it from shell-oriented siblings like exec_mac. The action enumeration makes the full surface of the tool visible without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It tells the agent the concrete situations this tool is for (lock screen, password dialogs, GUI interaction) and even routes one case away: long text should be pbcopy'd with exec_mac and pasted with cmd+v. It does not state an explicit when-not against exec_mac for general command execution, so it falls short of a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All NoMac toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources