MCP Screenshot Server

capture_screenshot

Capture full-screen, selected region, or a specific window screenshot to save or annotate. Choose capture mode and coordinates as needed.

Instructions

Capture a screenshot of the screen, a region, or a specific window.

On macOS, this uses the native screencapture command. On other systems, it uses PIL's ImageGrab or pyautogui as fallback.

For window capture on macOS, you need the numeric window ID (not the window name). You can find window IDs using: osascript -e 'tell app "System Events" to get id of windows of processes'

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	No	X coordinate for region capture
`y`	No	Y coordinate for region capture
`mode`	No	Capture mode: fullscreen, region (interactive selection), or window	fullscreen
`width`	No	Width for region capture
`height`	No	Height for region capture
`window_id`	No	Window ID for window capture (macOS). Use 'osascript' or 'GetWindowID' to find window IDs.

Output Schema

TableJSON Schema

Name	Required	Description
`width`	Yes	Image width in pixels
`height`	Yes	Image height in pixels
`message`	Yes	Status message
`image_id`	Yes	Unique identifier for the captured image

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 15, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden. It discloses the underlying implementations and platform differences, and notes the need for a numeric window ID. It does not detail side effects like file output or permissions, but the presence of an output schema likely covers return format, so this is adequate.

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?

The description is compact and efficient: the main purpose is front-loaded, and every sentence provides necessary detail (platform differences, window ID lookup) without fluff. It is well-structured across short paragraphs.

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 multiple modes and platform-specific behavior, the description covers the essential operational context: what modes exist, how to invoke them, and the platform fallback. Since an output schema exists, no return detail is needed, and the description fully equips an agent to call the tool correctly.

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

Parameters4/5

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

The input schema has 100% description coverage, with each parameter described clearly. The description adds extra value by explaining the window_id parameter more concretely (numeric ID, how to find it) and clarifies the region mode as interactive selection, which slightly extends the schema's basic definitions.

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 clearly states the tool captures a screenshot of the screen, region, or a specific window, with distinct verbs and resources. It is obviously distinct from the sibling tools, which are all for image annotation, editing, or management, not capture.

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 provides platform-specific guidance (macOS native screencapture vs PIL fallback) and explains the requirement for numeric window IDs on macOS, with a command to find them. It does not explicitly state when to use this tool over alternatives, but there are no competing capture tools among siblings, so the guidance is sufficient.

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