Chrome MCP Server Ngg
This project aims to build an MCP server that interacts with Chrome, including a simple demo version and a robust version based on the Python SDK, used for page screenshot and protocol validation.
rating : 2.5 points
downloads : 24
Introduction
This documentation provides an overview of the Chrome MCP Server, including its features, usage scenarios, and implementation details.Key Features
The server supports MCP protocol for communication with AI models in Chrome. It includes features such as initialization handshake, tool invocation, and protocol validation.Features
Protocol SupportFull support for the MCP protocol specification in Chrome environment.
Initialization HandshakeAutomated handshake process during server startup to establish communication with AI models.
Tool InvocationAbility to invoke specific tools through MCP protocol messages for tasks like screen capturing.
Advantages and Disadvantages
Advantages
Simplified implementation for learning purposes in demo version.
Production-ready code using MCP Python SDK in app/ directory.
Compliant with official MCP protocol specification.
Disadvantages
Demo version lacks error handling and logging.
Limited support for advanced MCP features in demo implementation.
Requires additional configuration for production use.
How to Use
Run the Server
Start the server using Uvicorn in demo mode or run production code from app/
Connect with MCP Client
Use MCP client tools to establish connection and send protocol messages.
Usage Examples
Learning MCP ProtocolAnalyze the initialization handshake process in demo mode.
Screen CapturingInvoke screen capture tool via MCP message for browser extension integration.
Frequently Asked Questions
What is the difference between demo and production versions?
How to integrate with other tools?
Resources
MCP Protocol Specification
Official documentation of MCP protocol.
Uvicorn Documentation
ASGI server for running Python web applications.
Featured MCP Services

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
140
4.5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
829
4.3 points

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
1.7K
5 points

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
86
4.3 points

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

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#
565
5 points

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
282
4.5 points

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
753
4.8 points