ScreenshotOne MCP Server

A simple implementation of an MCP server for the ScreenshotOne API

Catalog onlyCatalog onlySTDIO

Overview

MCP is a command-line tool and local user interface designed for discovering, installing, and managing Model Context Protocol (MCP) servers, acting as a broker between different clients and these servers.

To use MCP, install the tool and utilize command-line commands like mcp install <client>, mcp registry search <query>, and mcp package install <package[@<version>]> to manage your MCP servers.

Discover and install MCP servers from a public registry. - Manage OAuth2 credentials for server authentication and authorization. - Maintain an audit log of operations with a UI for reviewing. - Use Docker to run servers in a secure and isolated way without modifying the host environment.

Efficiently managing multiple MCP servers for AI clients like Claude and Zed.
Ensuring secure interactions with various servers through OAuth2 management.
Running and uninstalling servers seamlessly through CLI commands.

Add to your AI client

Use these steps to connect ScreenshotOne MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-screenshotone": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-screenshotone"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-screenshotone": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-screenshotone"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-screenshotone": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-screenshotone"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-screenshotone": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-screenshotone"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-screenshotone": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-screenshotone"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-screenshotone": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-screenshotone"
      ]
    }
  }
}

FAQ

What does MCP stand for?

MCP stands for Model Context Protocol, which is a framework for server-client interactions in AI environments.

Does MCP support all AI clients?

MCP currently supports clients such as Claude and Zed, with plans for broader compatibility in the future.

Is MCP a standalone server?

No, MCP acts as a broker and requires the installation of MCP servers that it can manage.

Developer tools