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
6.4K

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

Alternatives

A
Acemcp
Acemcp is an MCP server for codebase indexing and semantic search, supporting automatic incremental indexing, multi-encoding file processing, .gitignore integration, and a Web management interface, helping developers quickly search for and understand code context.
Python
7.7K
5 points
B
Blueprint MCP
Blueprint MCP is a chart generation tool based on the Arcade ecosystem. It uses technologies such as Nano Banana Pro to automatically generate visual charts such as architecture diagrams and flowcharts by analyzing codebases and system architectures, helping developers understand complex systems.
Python
7.7K
4 points
M
MCP Agent Mail
MCP Agent Mail is a mail - based coordination layer designed for AI programming agents, providing identity management, message sending and receiving, file reservation, and search functions, supporting asynchronous collaboration and conflict avoidance among multiple agents.
Python
8.4K
5 points
M
MCP
The Microsoft official MCP server provides search and access functions for the latest Microsoft technical documentation for AI assistants
12.8K
5 points
A
Aderyn
Aderyn is an open - source Solidity smart contract static analysis tool written in Rust, which helps developers and security researchers discover vulnerabilities in Solidity code. It supports Foundry and Hardhat projects, can generate reports in multiple formats, and provides a VSCode extension.
Rust
10.6K
5 points
D
Devtools Debugger MCP
The Node.js Debugger MCP server provides complete debugging capabilities based on the Chrome DevTools protocol, including breakpoint setting, stepping execution, variable inspection, and expression evaluation.
TypeScript
9.9K
4 points
S
Scrapling
Scrapling is an adaptive web scraping library that can automatically learn website changes and re - locate elements. It supports multiple scraping methods and AI integration, providing high - performance parsing and a developer - friendly experience.
Python
10.6K
5 points
M
Mcpjungle
MCPJungle is a self-hosted MCP gateway used to centrally manage and proxy multiple MCP servers, providing a unified tool access interface for AI agents.
Go
0
4.5 points
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
17.5K
4.5 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
18.2K
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
54.2K
4.3 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
27.2K
5 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#
22.9K
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
51.6K
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
18.1K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
75.3K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIBase