S

Screeny

The Screeny MCP Server is a privacy-first screenshot service designed specifically for macOS, allowing AI agents to securely capture screenshots of pre-approved application windows and providing a visual context for development and debugging tasks.
2.5 points
1

What is the Screeny MCP Server?

The Screeny MCP Server is a privacy-first tool designed specifically for macOS, allowing AI agents to securely capture screenshots of pre-approved application windows. It provides a secure visual context for development and debugging tasks.

How to use the Screeny MCP Server?

By configuring the MCP client (such as Claude Desktop or Cursor), you can authorize specific windows for screenshot capture. After setting up window approval using the command-line tool, you can obtain screenshot data through the API.

Applicable scenarios

Suitable for development and debugging scenarios that require secure screenshots, such as testing mobile app UIs and analyzing interface issues. Ensure that only windows approved by the user can be accessed.

Main features

Window approval systemOnly approved windows are allowed to be screenshot, ensuring that users have full control over which windows can be accessed.
Non-intrusive screenshotCapture window screenshots in the background without switching window focus or interrupting the current workflow.
Local processingAll screenshot processing is completed on your device and will not be sent to external servers, ensuring privacy and security.
Image compressionIf necessary, large-size images can be compressed to meet the 1MB limit for easy transmission and storage.

Advantages and limitations

Advantages
A powerful privacy protection mechanism ensures that only approved windows can be accessed.
Non-intrusive screenshot does not affect the user's normal operation.
Local processing avoids the leakage of sensitive data.
Limitations
Limited to the macOS platform and does not support other operating systems.
Users need to manually set screen recording permissions and window approval.

How to use

Grant screen recording permissions
In the system settings, add screen recording permissions for the terminal application and the MCP host (such as Claude Desktop or Cursor).
Install the Screeny MCP Server
Install the Screeny MCP Server using pipx or uvx. For example: `pipx install mcp-server-screeny`.
Configure the MCP client
Configure the Screeny MCP Server in Claude Desktop or Cursor to ensure the correct path.
Approve windows
Run `mcp-server-screeny --setup` and select the windows to be approved for subsequent screenshot capture.

Usage examples

Test the iOS simulator interfaceDuring the development process, use the Screeny MCP Server to directly capture screenshots from the iOS simulator to help quickly identify and fix UI issues.
Debug the application interfaceWhen encountering abnormal display of the application interface, use the Screeny MCP Server to capture screenshots of the relevant windows to help developers quickly locate the problem.

Frequently Asked Questions

What permissions do I need to use the Screeny MCP Server?
Why can't I see any approved windows?
How to solve the'spawn uvx ENOENT' error?

Related resources

Screeny MCP Server documentation
Official documentation providing detailed configuration and usage instructions.
GitHub repository
Project source code and contribution guidelines.
Installation guide
Step-by-step instructions for installing the Screeny MCP Server.
Installation
Copy the following command to your Client for configuration
{
  "mcpServers": {
    "screeny": {
      "command": "mcp-server-screeny",
      "args": []
    }
  }
}

{
  "mcpServers": {
    "screeny": {
      "command": "uvx",
      "args": ["mcp-server-screeny"]
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
Z
Zen MCP Server
Zen MCP is a multi-model AI collaborative development server that provides enhanced workflow tools and cross-model context management for AI coding assistants such as Claude and Gemini CLI. It supports seamless collaboration of multiple AI models to complete development tasks such as code review, debugging, and refactoring, and can maintain the continuation of conversation context between different workflows.
Python
46
5 points
C
Container Use
Container Use is an open-source tool that provides a containerized isolated environment for coding agents, supporting parallel development of multiple agents without interference.
Go
16
5 points
S
Search1api
The Search1API MCP Server is a server based on the Model Context Protocol (MCP), providing search and crawling functions, and supporting multiple search services and tools.
TypeScript
378
4 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
896
4.3 points
V
Video Editing MCP
Video Editor MCP is a video editing server that provides video upload, search, generation, and editing functions, supporting operations through the LLM and Video Jungle platforms.
Python
316
4 points
M
MCP Alchemy
Certified
MCP Alchemy is a tool that connects Claude Desktop to multiple databases, supporting SQL queries, database structure analysis, and data report generation.
Python
362
4.2 points
P
Postgresql MCP
A PostgreSQL database MCP service based on the FastMCP library, providing CRUD operations, schema inspection, and custom SQL query functions for specified tables.
Python
150
4 points
M
MCP Scan
MCP-Scan is a security scanning tool for MCP servers, used to detect common security vulnerabilities such as prompt injection, tool poisoning, and cross-domain escalation.
Python
661
5 points
Featured MCP Services
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
206
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.8K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
158
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
896
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
620
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
339
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
802
4.8 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIbase