Jason's MCP Servers: Universal Adapter for AI Applications

This repository contains setup and configuration files for various Model Context Protocol (MCP) servers used in my environment.

Included MCP Servers

1. puppeteer - Web browser automation and scraping, offering powerful control over web applications.
2. memory - Knowledge graph and memory management with advanced indexing and retrieval capabilities.
3. filesystem - File system operations and management for seamless access to local storage resources.
4. github - GitHub API integration for secure and efficient interaction with repositories.
5. weather - Weather information service for real-time data on climate conditions.
6. brave_search - Brave search API integration enabling high-performance web searches.
7. fetch - URL fetching and web content retrieval, providing robust methods to access online resources.
8. desktopCommander - Desktop command execution from wonderwhy-er/ClaudeComputerCommander for enhanced system interaction.

Installation

The install.sh (for Linux/Mac) and install.bat (for Windows) scripts will help you set up all the MCP servers in this repository. These scripts fetch servers from:

• The official Model Context Protocol organization repository at https://github.com/modelcontextprotocol/servers for most servers
• The ClaudeComputerCommander repository at https://github.com/wonderwhy-er/ClaudeComputerCommander for the desktop-commander server

The installation scripts will:

1. Clone the main repository
2. Set up each server in its own directory with the necessary dependencies
3. Install all required npm packages

Uninstallation

If you need to remove the MCP servers, you can use the provided uninstallation scripts:

• For Windows: Run uninstall.bat
• For Linux/Mac: Run uninstall.sh

These scripts will:

1. Warn you about what will be removed
2. Ask for confirmation before proceeding
3. Stop any running MCP server processes
4. Remove all MCP server directories
5. Optionally remove the entire mcp-servers directory

Server Structure

The Model Context Protocol servers repository has all servers in a single repository under the src directory. Our installation scripts:

1. Clone the entire repository
2. Create separate directories for each server
3. Copy the appropriate server code to each directory
4. Set up dependencies for each server
5. For the desktop-commander server, we get it from a separate repository

Requirements

• Node.js (v16 or higher) - https://nodejs.org/
• Git - https://git-scm.com/
• Python (3.8+ for some servers) - https://www.python.org/downloads/
• Docker (optional, for containerized deployment) - https://www.docker.com/products/docker-desktop/

API Requirements

Some MCP servers require API keys to function properly:

• GitHub API - https://github.com/settings/tokens
• Weather API - https://openweathermap.org/api or similar service
• Brave Search API - https://brave.com/search/api/

Configuration

See the individual server directories for specific configuration options. The config directory contains default configurations for all servers that you can customize according to your needs.

Environment Variables

Copy the .env.template file to .env and fill in your API keys and other required credentials before starting the servers.

License

MIT License

Puppeteer MCP Server: Web Browser Automation & Scraping

Overview: What is Puppeteer MCP Server?

Puppeteer is an MCP server designed for web browser automation and scraping, enabling AI applications to interact with web pages in a headless mode. It provides a robust set of features like page navigation, form filling, automated testing, and content extraction.

🔧 Core Features & MCP Capabilities

• Web Automation: Puppeteer can automate complex tasks on web applications.
• Scraping: Extract structured data from websites using JavaScript.
• Headless Mode: Perform actions without opening a browser UI for efficiency.
• API Integration: Integrate with AI workflows by providing real-time web content.

⚙️ MCP Architecture & Protocol Implementation

Puppeteer adheres to the Model Context Protocol, ensuring compatibility and standardization across different AI applications. The protocol flow is designed to be lightweight yet feature-rich, facilitating seamless data exchange.

🚀 Getting Started with Installation

1. Clone this repository: git clone https://github.com/jasons-mcp-servers/mcp-servers.git
2. Navigate to the Puppeteer directory: cd puppeteer
3. Install dependencies using npm: npm install

💡 Key Use Cases in AI Workflows

• AI Testing: Automated testing of web applications with real-world scenarios.
• Data Aggregation: Reliable scraping for data-driven insights.

🔌 Integration with MCP Clients

Puppeteer supports full integration with Claude Desktop, Continue, and Cursor. For example, an AI application can use Puppeteer to navigate a website, fill out forms, and extract relevant data for further processing.

📊 Performance & Compatibility Matrix

MCP Client	Resources	Tools	Prompts	Status
Claude Desktop	✅	✅	✅	Full Support
Continue	✅	✅	X	Partial Support
Cursor	X	✅	✅	Limited Use

🛠️ Advanced Configuration & Security

Configure Puppeteer in your environment by setting up proxy settings and API keys. Ensure security by encrypting sensitive information.

❓ Frequently Asked Questions (FAQ)

1. Q: How do I integrate Puppeteer with my AI application? A: Use the MCP protocol to interact with Puppeteer servers, enabling seamless automation and scraping.
2. Q: What compatibility issues might arise? A: Ensure your AI application supports web automation using MCP.
3. Q: Can Puppeteer handle complex websites? A: Yes, Puppeteer is designed for handling any complexity in web applications.
4. Q: Are there any security concerns with scraping websites? A: Follow ethical guidelines and ensure compliance with the scraped site's terms of service.

👨‍💻 Development & Contribution Guidelines

1. Fork this repository on GitHub.
2. Make changes to the Puppeteer codebase.
3. Test your modifications thoroughly.
4. Submit a pull request for review.

🌐 MCP Ecosystem & Resources

Explore the broader MCP ecosystem at modelcontextprotocol.org and contribute to the community forums for additional discussions.

---

Memory MCP Server: Knowledge Graph & Memory Management

Overview: What is Memory MCP Server?

Memory is an advanced MCP server that combines a knowledge graph with powerful memory management features. It enables AI applications like Claude Desktop, Continue, and Cursor to maintain and retrieve contextual information efficiently.

🔧 Core Features & MCP Capabilities

• Knowledge Graph: Represent and query large volumes of structured data.
• Memory Management: Optimize storage and retrieval for scalable applications.
• Advanced Indexing: Enable fast searches through vast datasets.

⚙️ MCP Architecture & Protocol Implementation

The Memory server implements the Model Context Protocol to ensure compatibility with other MCP-enabled clients. The protocol flow is designed to handle complex indexing operations and queries.

🚀 Getting Started with Installation

1. Clone this repository: git clone https://github.com/jasons-mcp-servers/mcp-servers.git
2. Navigate to the Memory directory: cd memory
3. Install dependencies using npm: npm install

💡 Key Use Cases in AI Workflows

• Contextual Understanding: Provide detailed context for natural language processing.
• Data Retrieval: Accurately fetch data from a knowledge graph.

🔌 Integration with MCP Clients

Memory supports full integration with Claude Desktop, Continue, and Cursor. For example, an AI application can use Memory to query a knowledge graph and return relevant results quickly.

📊 Performance & Compatibility Matrix

MCP Client	Resources	Tools	Prompts	Status
Claude Desktop	✅	✅	✅	Full Support
Continue	✅	X	✅	Limited Use
Cursor	📋	✅	✅	Full Support

🛠️ Advanced Configuration & Security

Configure Memory in your environment by setting up API keys, proxy settings, and database configurations. Ensure data security by encrypting sensitive information.

❓ Frequently Asked Questions (FAQ)

1. Q: How do I integrate Memory with my AI application? A: Use the MCP protocol to interact with Memory servers, enabling efficient knowledge retrieval.
2. Q: What compatibility issues might arise? A: Ensure your AI application supports memory management using MCP.
3. Q: Can Memory handle large datasets? A: Yes, Memory is designed for handling extensive collections of data.
4. Q: Are there any security concerns with storing sensitive information in the knowledge graph? A: Follow best practices to secure your data and comply with privacy regulations.

👨‍💻 Development & Contribution Guidelines

1. Fork this repository on GitHub.
2. Make changes to the Memory codebase.
3. Test your modifications thoroughly.
4. Submit a pull request for review.

🌐 MCP Ecosystem & Resources

Explore the broader MCP ecosystem at modelcontextprotocol.org and contribute to the community forums for additional discussions.

---

Model Context Protocol Flow Diagram

graph TD
    A[AI Application] -->|MCP Client| B[MCP Protocol]
    B --> C[MCP Server]
    C --> D[Data Source/Tool]
    style A fill:#e1f5fe
    style C fill:#f3e5f5
    style D fill:#e8f5e8

Model Context Protocol Client Compatibility Matrix

MCP Client	Resources	Tools	Prompts	Status
Claude Desktop	✅	✅	✅	Full Support
Continue	✅	✅	❌	Partial Support
Cursor	✅	✏️	✅	Limited Use

Example MCP Configuration Sample

{
  "mcpServers": {
    "puppeteer": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-puppeteer"],
      "env": {
        "API_KEY": "your-api-key"
      }
    },
    "memory": {
      "command": "node",
      "args": ["server/main.js"]
    }
  }
}

---

This comprehensive documentation covers the Jason’s MCP servers, ensuring they are fully integrated with modern AI applications while maintaining strict compliance with Model Context Protocol standards. For further assistance or detailed implementations, please refer to specific guides and community resources available within the MCP ecosystem.