mcp

MCP.Pizza Chef: screenshotone

The ScreenshotOne MCP server is an official implementation of the Model Context Protocol server designed to integrate with the ScreenshotOne API. It enables real-time rendering of website screenshots as images, facilitating seamless interaction between LLMs and web content. This server simplifies capturing visual context from websites, supporting developers and AI workflows that require up-to-date visual data.

Use This MCP server To

Render website screenshots on demand for visual context Integrate website image capture into AI workflows Provide real-time website visuals to LLMs for analysis Automate screenshot generation for monitoring web changes Embed website snapshots in chat or documentation tools

README

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.

Tools

render-website-screenshot: Render a screenshot of a website and returns it as an image.

Usage

Build it

Always install dependencies and build it first:

npm install && npm run build

Get your ScreenshotOne API key

With Claude for Desktop

Add the following to your ~/Library/Application\ Support/Claude/claude_desktop_config.json:

{
    "mcpServers": {
        "screenshotone": {
            "command": "node",
            "args": ["path/to/screenshotone/mcp/build/index.js"],
            "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.

mcp FAQ

How do I get started with the ScreenshotOne MCP server?

Install dependencies, build the project, and obtain an API key from ScreenshotOne to configure the server.

What functionality does the render-website-screenshot tool provide?

It captures and returns screenshots of websites as images for use in AI workflows.

Can this MCP server be used with multiple LLM providers?

Yes, it is compatible with models like OpenAI, Claude, and Gemini through the MCP protocol.

Is the ScreenshotOne MCP server open source?

Yes, it is available on GitHub for review, customization, and contribution.

How do I configure the server for use with Claude for Desktop?

Add the server details to the claude_desktop_config.json file as specified in the documentation.

What are the prerequisites for running this MCP server?

Node.js environment, ScreenshotOne API key, and network access to the ScreenshotOne service.

Does the server support real-time screenshot rendering?

Yes, it provides on-demand rendering of website screenshots in real time.

Can I extend the server with additional tools?

The server architecture supports adding more MCP tools to expose new functionalities.