Que pouvez-vous faire avec ScreenshotOne ?
render-website-screenshot: Render a website screenshot and return temporary screenshot, content, and slice URLs as requested.extract-website-markdown: Render a website and return its cleaned Markdown directly as text.get-usage: Get ScreenshotOne API quota and concurrency usage.urlblock_banners(defaults totrue)block_ads(defaults totrue)image_quality(defaults to80)full_page(defaults tofalse)
Installation
Les étapes d'installation sont dans la documentation ci-dessous. Documentation
Documentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
ScreenshotOne MCP Server
An official implementation of an MCP (Model Context Protocol) server for ScreenshotOne.
A few more words about why it was built and some thoughts about the future of MCP.
ScreenshotOne also offers an official hosted MCP server. See the ScreenshotOne MCP integration for setup instructions and the latest updates.
Tools
render-website-screenshot: Render a website screenshot and return temporary screenshot, content, and slice URLs as requested.extract-website-markdown: Render a website and return its cleaned Markdown directly as text.get-usage: Get ScreenshotOne API quota and concurrency usage.
The screenshot tool exposes these focused options:
urlblock_banners(defaults totrue)block_ads(defaults totrue)image_quality(defaults to80)full_page(defaults tofalse)full_page_slices(defaults tofalse; requiresfull_page=true)metadata_content(defaults tofalse)metadata_content_format(htmlormarkdown; requiresmetadata_content=true)
The option names and values for metadata content and full-page slices match the ScreenshotOne API. The tool does not expose response-type or cache controls; it always requests a JSON response with API caching disabled.
Set metadata_content=true and metadata_content_format=markdown to receive a temporary Markdown content URL with the screenshot. Set full_page=true and full_page_slices=true to receive smaller vertical screenshot URLs. Slices are preferred when an AI agent needs to analyze a long page that may not be handled reliably as one large image.
A successful capture returns the requested URLs as text and structured content:
{
"url": "https://<screenshotone-cache-domain>/...",
"content": {
"url": "https://<screenshotone-cache-domain>/...",
"expires": "Sun, 07 Sep 2026 12:00:00 GMT",
"format": "markdown"
},
"slices": [
{
"index": 0,
"offset_y": 0,
"width": 1280,
"height": 4000,
"url": "https://<screenshotone-cache-domain>/..."
}
]
}
The URLs are temporary. The screenshot URL is available for up to four hours, while metadata content includes its exact expiration time. Download any artifact you need to keep.
extract-website-markdown accepts only url. It is a focused shortcut for ScreenshotOne's format=markdown API request and returns the resulting Markdown directly in one MCP text response. Use it when the agent needs to read or analyze page content without a screenshot.
Usage
Build it
Always install dependencies and build it first:
npm install && npm run build
Get your ScreenshotOne API key
Sign up at ScreenshotOne and get your API key.
Run with npx
Run the CLI directly from the npm package without cloning the repository:
SCREENSHOTONE_API_KEY=your_api_key npx --yes @screenshotone/mcp
With Claude for Desktop
Add the following to your ~/Library/Application\ Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"screenshotone": {
"command": "npx",
"args": ["--yes", "@screenshotone/mcp"],
"env": {
"SCREENSHOTONE_API_KEY": "<your api key>"
}
}
}
}
Standalone or for other projects
SCREENSHOTONE_API_KEY=your_api_key node build/index.js
License
ScreenshotOne MCP Server is licensed under the MIT License.
Questions fréquentes
Qu'est-ce que ScreenshotOne ?
Render website screenshots with ScreenshotOne
Comment installer ScreenshotOne ?
Suivez les étapes d'installation de sa documentation, affichée sur cette page et dans son dépôt.
ScreenshotOne est-il open source ?
Oui. Son code est sur GitHub sous licence MIT.
Qui maintient ScreenshotOne ?
Il est publié par screenshotone. AI.tn le référence sans le maintenir ni le recommander.
Issu des listes communautaires awesome-mcp-servers et du dépôt GitHub du projet. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.