MCP Screenshot MCP Server

A Model Context Protocol server that provides screenshot and OCR capabilities

Local serverstdio

What is the MCP Screenshot MCP server?

Mcp screenshot mcp server connects MCP Screenshot to AI assistants that speak the Model Context Protocol. A Model Context Protocol server that provides screenshot and OCR capabilities.

What MCP Screenshot does

An MCP server that captures screenshots and performs OCR text recognition.

Key capabilities

  • Screenshot capture (left half, right half, full screen)
  • OCR text recognition (supports Japanese and English)
  • Multiple output formats (JSON, Markdown, vertical, horizontal)

Tools it exposes

Once connected, the assistant can call this tool directly:

  • capture — Options: - region: Screenshot area ('left'/'right'/'full', default: 'left') - format: Output format ('json'/'markdown'/'vertical'/'horizontal', default

Installing the mcp screenshot mcp server

The server is distributed via npm as @kazuph/mcp-screenshot, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

Before the server will start you need to supply one environment variable: OCR_API_URL. Keep credentials in your client's env block or a secrets manager rather than committing them.

Where it fits

Browser automation servers are the ones people reach for when a site has no API — the assistant drives a real page instead of guessing at endpoints. MCP Screenshot sits in that group, and the shape of its toolset — capture — tells you what it is really for. Worth comparing against the other browser automation servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • Maintained by kazuph.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the mcp screenshot mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
captureOptions: - region: Screenshot area ('left'/'right'/'full', default: 'left') - format: Output format ('json'/'markdown'/'vertical'/'horizontal', default: 'markdown')

How to install the MCP Screenshot MCP server

{
  "mcpServers": {
    "screenshot": {
      "command": "npx",
      "args": ["-y", "@kazuph/mcp-screenshot"],
      "env": {
        "OCR_API_URL": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
OCR_API_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use MCP Screenshot to capture.

Frequently asked questions

It connects MCP Screenshot to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (capture) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Screenshot directly.