Skip to main content
Glama

Screeny MCP Server

by rohanrav
MIT License
2
  • Apple

Screeny Banner

Screeny MCP Server: Privacy first macOS Screenshots for AI Agents

A privacy-first, macOS-only MCP server that enables LLMs to capture screenshots of pre-approved application windows, providing secure visual context for development and debugging tasks.

🔒 Privacy-First Design

Unlike other screenshot tools, Screeny requires explicit user approval for each window before it can be captured:

  • Window approval system - Only pre-approved windows can be captured
  • User-controlled access - You decide exactly which windows are accessible
  • Non-intrusive capture - Screenshots taken in background without changing window focus or interrupting your workflow
  • Local storage - Approvals saved locally in ~/.screeny/approved_windows.json

Important

Requires Screen Capture permission + Window Approval Setup - see instructions below.

Available Tools

  • listWindows - Lists all approved application windows available for screenshot capture.
    • Only shows user approved windows
  • takeScreenshot - Captures a screenshot of a specific window by its ID.
    • Captures windows in background - no need to bring window to front, but cannot capture minimized windows
    • Provides actual pixel data - full-fidelity image, not OCR or text extraction
    • Can compress image - if needed, compresses large images to fit within 1MB

Resources

  • screeny://info - Server information and configuration details

Configuration

Claude Desktop

  1. Open Claude settings → Developer → Edit Config
  2. Add configuration
  3. Restart Claude Desktop after saving config

First install with: pipx install mcp-server-screeny

{ "mcpServers": { "screeny": { "command": "mcp-server-screeny", "args": [] } } }

Note: If you get an ENOENT error, replace "mcp-server-screeny" with the full path to the executable (find it with which mcp-server-screeny in your terminal).

{ "mcpServers": { "screeny": { "command": "uvx", "args": ["mcp-server-screeny"] } } }

Note: If you get a "spawn uvx ENOENT" error, replace "uvx" with the full path to uvx:

which uvx # Find your uvx path

Then use that full path in the config (e.g., "/opt/homebrew/bin/uvx").

Cursor

  1. Open Cursor settings → Tools & Integrations → MCP Tools
  2. Add configuration
  3. Restart Cursor after saving config

First install with: pipx install mcp-server-screeny

{ "mcpServers": { "screeny": { "command": "mcp-server-screeny", "args": [] } } }

Note: If you get an ENOENT error, replace "mcp-server-screeny" with the full path to the executable (find it with which mcp-server-screeny in your terminal).

{ "mcpServers": { "screeny": { "command": "uvx", "args": ["mcp-server-screeny"] } } }

Note: If you get a "spawn uvx ENOENT" error, replace "uvx" with the full path to uvx:

which uvx # Find your uvx path

Then use that full path in the config (e.g., "/opt/homebrew/bin/uvx").

Setup

1. Grant Screen Capture Permission (Required)

Important: Grant permission before running window approval.

Note: You need to grant Screen Capture permission to BOTH:

  1. Your Terminal application (Terminal.app, iTerm2, etc.) - Required for running setup (can be disabled after)
  2. Your MCP host (Claude Desktop, Cursor) - Required for taking screenshots

To add them:

  1. Open System Settings > Privacy & Security > Screen & System Audio Recording
  2. Click the "+" button
  3. Add your Terminal application AND your MCP host application
  4. Restart both applications after granting permissions

2. Window Approval (Required)

After configuring your MCP client above, approve which windows can be captured.

# Interactive approval mcp-server-screeny --setup # Auto-approve all current windows mcp-server-screeny --setup --allow-all
# Interactive approval uvx mcp-server-screeny --setup # Auto-approve all current windows uvx mcp-server-screeny --setup --allow-all

Approvals are saved to ~/.screeny/approved_windows.json. Re-run setup when you want to update the list of approved windows.

Security & Privacy

  • Only user-approved windows can be captured
  • All processing stays local on your machine
  • Screenshots are temporary and deleted immediately after use

Troubleshooting

Permission Issues

# Test window detection and permissions mcp-server-screeny --debug # Re-run setup if windows changed mcp-server-screeny --setup

Common Issues

"spawn uvx ENOENT" error

  • Solution: Use the full path to uvx in your MCP config instead of just "uvx"
  • Find path with: which uvx
  • Example: "/opt/homebrew/bin/uvx" or "/usr/local/bin/uvx"

"No approved windows found"

  • Solution: Run mcp-server-screeny --setup first (or uvx mcp-server-screeny --setup if using uvx)

"Screen Recording permission required" or "No windows found"

  • Solution: Grant Screen Recording permission in System Settings > Privacy & Security > Screen & System Audio Recording
    • Click "+" button and manually add your MCP host (Claude Desktop, Cursor, etc.)
    • Restart your MCP host application after granting permissions
  • Try running setup again after granting permissions

Contributing

Pull requests are welcome! Feel free to contribute new ideas, bug fixes, or enhancements.

This is my first MCP project - if you encounter any bugs, please open an issue and I'll do my best to fix them!

I created this tool to streamline my mobile development workflow. I was tired of manually taking screenshots repeatedly to describe UI issues. With Screeny, Cursor can directly capture screenshots of my iOS simulator and iterate on the design in a loop. I'm excited to see how others will use this!

Requirements

  • Python 3.10+
  • macOS
  • Screen Capture permission

License

MIT License

-
security - not tested
A
license - permissive license
-
quality - not tested

A privacy-first macOS MCP server that enables AI agents to capture screenshots of pre-approved application windows for development and debugging tasks.

  1. 🔒 Privacy-First Design
    1. Available Tools
      1. Resources
    2. Configuration
      1. Claude Desktop
      2. Cursor
    3. Setup
      1. Grant Screen Capture Permission (Required)
      2. Window Approval (Required)
    4. Security & Privacy
      1. Troubleshooting
        1. Permission Issues
        2. Common Issues
      2. Contributing
        1. Requirements
          1. License

            Related MCP Servers

            • A
              security
              A
              license
              A
              quality
              An official MCP server implementation that allows AI assistants to capture website screenshots through the ScreenshotOne API, enabling visual context from web pages during conversations.
              Last updated -
              1
              4
              21
              TypeScript
              MIT License
              • Apple
            • -
              security
              F
              license
              -
              quality
              Enables AI tools to capture and process screenshots of a user's screen, allowing AI assistants to see and analyze what the user is looking at through a simple MCP interface.
              Last updated -
              1
              Python
              • Linux
              • Apple
            • A
              security
              A
              license
              A
              quality
              A server that captures screenshots from iOS Simulator using the Model Context Protocol (MCP) and saves them to a specified directory.
              Last updated -
              1
              15
              TypeScript
              MIT License
              • Apple
            • -
              security
              -
              license
              -
              quality
              An MCP server that provides web development tools including taking screenshots of screens, enabling AI agents to capture and analyze visual content during development.
              Last updated -
              2
              TypeScript

            View all related MCP servers

            MCP directory API

            We provide all the information about MCP servers via our MCP API.

            curl -X GET 'https://glama.ai/api/mcp/v1/servers/rohanrav/screeny'

            If you have feedback or need assistance with the MCP directory API, please join our Discord server