Server for MCP Protocol with On-Screen UI Interaction

Glama

Search for:

Server for MCP Protocol with On-Screen UI Interaction

View all MCP Servers

Why this server?
Provides screenshot and OCR capabilities for macOS, allowing the AI to 'see' the screen.
mcp-screenshot
kazuph
A
security
A
license
A
quality
Provides screenshot and OCR capabilities for macOS.
1
35
10
JavaScript
MIT License
Why this server?
Automates interactions with SAP GUI, allowing precise control through actions like clicking, typing, and scrolling in the SAP interface.
MCP SAP GUI Server
mario-andreschak
Verified
-
security
A
license
-
quality
Automates interactions with SAP GUI using the Model Context Protocol, allowing precise control of SAP transactions through tools like clicking, typing, scrolling, and transaction management.
9
Python
MIT License
Why this server?
Enables control over Windows system operations, including mouse and keyboard control, window management, and screen capture.
MCPControl
Cheffromspace
Verified
-
security
A
license
-
quality
A Windows control server built using nut.js and Model Context Protocol (MCP), providing programmatic control over Windows system operations including mouse, keyboard, window management, and screen capture functionality.
189
43
TypeScript
MIT License
Why this server?
Enables the AI to control web browsers and interact with web pages.
Playwright MCP Server
lebrodus
A
security
F
license
A
quality
A server that enables browser automation using Playwright, allowing interaction with web pages, capturing screenshots, and executing JavaScript in a browser environment through LLMs.
12
15,918
1
TypeScript
Why this server?
Facilitates the capture of screenshots of web pages and local HTML files.
MCP Screenshot Server
sethbang
-
security
F
license
-
quality
Enables capturing screenshots of web pages and local HTML files through a simple MCP tool interface using Puppeteer with configurable options for dimensions and output paths.
1
0
4
JavaScript
Why this server?
Enables browser automation through Selenium, allowing interaction with web elements and performing user actions.
MCP Selenium
angiejones
Verified
-
security
A
license
-
quality
Enables browser automation using the Selenium WebDriver through MCP, supporting browser management, element location, and both basic and advanced user interactions.
175
21
JavaScript
MIT License
Why this server?
Enables users to send live webcam images to MCP clients, facilitating interaction through capturing images, screenshots, and providing a webcam view for visual input.
MCP Webcam Server
evalstate
A
security
A
license
A
quality
Enables users to send live webcam images to Claude Desktop or other MCP clients, facilitating interaction through capturing images, screenshots, and providing a webcam view for visual input.
2
143
15
TypeScript
MIT License
Why this server?
An AI-powered development toolkit for Cursor providing intelligent coding assistance through advanced reasoning, UI screenshot analysis, and code review tools.
AI Development Assistant MCP Server
kleneway
-
security
A
license
-
quality
An AI-powered development toolkit for Cursor providing intelligent coding assistance through advanced reasoning, UI screenshot analysis, and code review tools.
1,679
240
TypeScript
MIT License
Why this server?
Automatic operation of on-screen GUI.
omniparser-autogui-mcp
NON906
Verified
-
security
A
license
-
quality
Automatic operation of on-screen GUI.
17
Python
MIT License
Why this server?
Enables AI agents to control web browsers using natural language, featuring automated browsing, form filling, vision-based element detection, and structured JSON responses for systematic browser control.
MCP Browser Use Server
JovaniPink
A
security
F
license
A
quality
Enables AI agents to interact with web browsers using natural language, featuring automated browsing, form filling, vision-based element detection, and structured JSON responses for systematic browser control.
1
23
Python