MCP Screenshot Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| take_screenshotB | Capture web page or element via headless browser. Saves to ~/Documents/screenshots by default (configurable via SCREENSHOT_OUTPUT_DIR env var). |
| take_system_screenshotA | Capture desktop, window, or region screenshot. Cross-platform: macOS (screencapture), Linux (maim/scrot/gnome-screenshot/etc.), Windows (PowerShell+.NET). Saves to ~/Documents/screenshots by default (configurable via SCREENSHOT_OUTPUT_DIR env var). For window mode, provide windowName (app name like "Safari") or windowId. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools split cleanly along rendering source: headless browser page capture vs. OS-level desktop/window/region capture, and descriptions make this explicit. Minor risk remains because the generic name 'take_screenshot' doesn't signal 'web page only', so an agent skimming names could pick it for a desktop capture.
Both follow the same verb_noun convention (take_screenshot, take_system_screenshot) with a consistent qualifier modifier. Predictable and readable as a set.
Two tools are proportionate for a narrow screenshot-capture domain, and each covers a genuinely separate surface. It is on the thin side — a third tool (e.g., listing or re-opening saved captures) would round out the set.
Core capture scenarios are covered: web pages (including elements) and desktop, window, or region captures across all three OSes, with configurable output. Minor gaps around browsing/retrieving saved screenshots or format/full-page options, but agents can work around these via the filesystem.