# OpenScreenShot [Health: Active]

**Category:** 💻 Developer Tools  
**Repository:** https://github.com/PGHQdev/OpenScreenShot  
**GitHub Stars:** 81  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/openscreenshot

## Description
Capture website screenshots (viewport or full page) with your installed Chrome. Runs locally.

## Claude Desktop Quick Installation
Heuristic fallback — verify the package name and runner against the repository README before running it. Uses `npx` (confidence: low):

```json
"mcpServers": {
  "openscreenshot": {
    "command": "npx",
    "args": ["-y","openscreenshot"]
  }
}
```

## Documentation

## What OpenScreenShot MCP server does

OpenScreenShot MCP server provides local website screenshot capture through an installed browser. The documented capture modes include the currently visible area, a selected region, and the complete scrolling page. Full-page capture can include content behind sticky headers and inside nested scrollable areas.

The project is also distributed as a browser extension for Chrome and Chromium-based browsers, as well as Firefox. The extension includes editing and export features around captured images. These include cropping, arrows, text, numbered steps, spotlight effects, blur or redaction, undo, clipboard copying, and image or PDF export.

The README presents MCP as a local server with client setup required. It does not provide the names, schemas, or invocation details for individual MCP tools in the supplied material.

## How it works

Capture and editing are performed locally in the browser. The extension requests access to the active tab when the user clicks the extension, uses a shortcut, or chooses a capture action from the context menu. It does not have standing access to every website because its listed host permissions are empty.

Captured images, recordings, and edits remain in local browser storage until they are exported or deleted. This makes the OpenScreenShot MCP server a fit for workflows where page content should remain on the local machine rather than being uploaded to a screenshot API.

The extension can capture a full page by scrolling and stitching page content. Visible-area and region capture are available from the context menu or keyboard shortcuts. An element-capture mode exists in source builds, but the README says it has not been released through the browser stores.

## Setup and configuration

Install the browser extension from the Chrome Web Store or Firefox Add-ons, then pin it to the browser toolbar. The basic workflow is to open a page, activate the extension, capture the page, and edit or export the result.

For Firefox, the README requires desktop Firefox 140 or later. The Chrome extension also works in Edge, Brave, Arc, and other Chromium browsers. The MCP entry is described as a local server, and an MCP client must be configured separately; the supplied material does not include a command, package name, transport, or client-specific configuration example.

Express mode controls whether clicking the extension immediately captures the whole page or opens a capture menu. It can be disabled in settings when a menu is preferred.

## Tools and capabilities

The documented capture and output capabilities include:

- Full-page, visible-area, and selected-region screenshots
- Local annotation with arrows, text, numbered steps, spotlight, and crop
- Blur and redaction for information that should not be shared
- PNG, JPEG, WebP, multi-page PDF, and clipboard export
- Local editing history and browser storage

Chrome supports tab recording with click-focused auto-zoom, microphone and webcam input, trimming, and selectable recording regions. Recording is not available in Firefox. The README does not establish that every extension feature is exposed as a separate MCP tool.

## Limitations and notes

The MCP server requires an MCP client configuration, but the supplied README excerpt does not document supported client names or installation commands. Browser permissions are action-based: active-tab access is granted when a capture action is initiated, while broader access may be requested by Chrome for recording across sites. Firefox does not request recording permissions.

Screen-wide color picking and floating capture windows depend on browser support. Element capture is limited to source builds until it is released through the browser stores. Content inside an iframe is captured as part of that iframe's visible rectangle, and an element must be fully visible for element capture; clipped elements can instead use the full-page fallback.

_Full upstream README: https://allmcps.com/mcp/openscreenshot/readme_