Skip to main content
Glama
dockndevai

mcp-mac-control

by dockndevai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Screenshot

screenshot
Read-onlyIdempotent

Capture a display as a PNG image downscaled to match click coordinates. Specify a display or use the frontmost window's display automatically for GUI automation.

Instructions

Capture a display as a PNG and return it. The image is downscaled to POINTS, so it is 1:1 with click coordinates. Omit display to capture the display holding the frontmost window (handy with a second monitor); pass 0 for the main display. Needs Screen Recording permission.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
displayNoWhich display to capture (0 = main). Omit for the frontmost window's display.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.1
    • addedInput schema / properties / display
      Added value: +{
+  "description": "Which display to capture (0 = main). Omit for the frontmost window's display.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses that the image is downscaled to points so it is 1:1 with click coordinates, which is key behavioral information. It also calls out the Screen Recording permission prerequisite. This is material context the annotations do not convey, and there is no contradiction with them.

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

Conciseness5/5

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

Three short sentences deliver the core action, coordinate-mapping behavior, display selection modes, and permission requirement. The most important information is front-loaded, and there is no filler.

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

Completeness5/5

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

For a tool with one optional parameter, rich annotations, and no output schema, the description covers what the tool returns, how the image maps to click coordinates, how to select displays, and what permission is needed. Nothing required to invoke it correctly is missing.

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?

The input schema already documents display with 100% coverage, including the 0=main and omit-for-frontmost behavior. The description mostly paraphrases the schema, adding only the 'handy with a second monitor' convenience note, so the schema carries the semantic weight.

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?

The description opens with 'Capture a display as a PNG and return it', which names a specific verb, resource, and output format. This clearly separates it from siblings like get_screen_size, which reports dimensions rather than producing an image.

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 gives clear context for both invocation styles: omit display for the frontmost window's display and pass 0 for the main display, with a practical second-monitor note. It does not explicitly contrast with sibling alternatives or state when not to use the tool, so it falls just short of a 5.

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

Deploy Server

Other Tools