OpenScreenShot
OfficialServer 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 |
|---|---|
| capture_screenshotA | Capture a PNG screenshot of a public web page locally via the system Chrome. Use redact to cover elements, text patterns, or rectangles with black boxes before the screenshot is taken. The capture fails with no image if a selector matches nothing or the page changes during the capture. |
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 1 tool
With only one tool, there is no possibility of confusing it with another; its purpose (capture a PNG screenshot of a URL with optional redaction) is unambiguous.
The single name capture_screenshot follows a clean verb_noun snake_case convention, and nothing in the set deviates from it.
A one-tool server is defensible for a narrow, focused purpose, but it sits at the thin end of the scale with no batching, waiting, or alternate-output operations.
Core capture with redaction is covered, but the surface omits common needs such as full-page vs viewport control, wait/ready conditions, custom headers, cookies/auth, and alternate formats like PDF, leaving plausible agent requests unserved.