MCP Servers

A collection of Model Context Protocol servers, templates, tools and more.

MCP Server test repository - Cursor integration

Created 11/5/2025
Updated about 1 month ago
Repository documentation and setup instructions

🚀 MCP Servers Collection

License: MIT MCP GitHub

A curated collection of Model Context Protocol (MCP) servers for seamless integration with AI development tools like Cursor, enabling powerful context-aware coding experiences.

📖 Table of Contents

🤔 What is MCP?

Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to Large Language Models (LLMs). It enables AI assistants to securely access external tools, APIs, and data sources in a controlled manner.

Key Benefits:

  • 🔌 Universal Integration: Connect AI models to any data source or tool
  • 🔒 Secure Access: Fine-grained permission control for external resources
  • Real-time Data: Access up-to-date information from APIs and databases
  • 🛠️ Extensible: Build custom servers for your specific needs
  • 🌐 Cross-platform: Works with multiple AI development environments

✨ Features

  • GitHub Integration: Full GitHub API access through MCP
  • Easy Configuration: Simple JSON-based setup
  • Token Management: Secure credential handling
  • Multi-server Support: Run multiple MCP servers simultaneously
  • Real-time Updates: Live data access from external sources
  • Error Handling: Robust error reporting and debugging

🛠️ Available MCP Servers

This repository includes configurations and examples for the following MCP servers:

1. MCP Generator ⚡ NEW!

A meta-MCP server that generates other MCP servers!

The MCP Generator is a revolutionary tool that automates the creation of MCP servers. Instead of manually writing boilerplate code, simply describe what you want and the generator creates a complete, production-ready MCP server for you.

Capabilities:

  • 🏗️ Generate complete MCP servers from templates
  • 🛠️ Support for tool-based, resource-based, and full-featured servers
  • 📝 Automatic file structure creation (server.py, README.md, requirements.txt)
  • ✅ Built-in configuration validation
  • 📚 Example configurations for quick start
  • 🎯 Interactive code generation through AI assistants

Use Cases:

  • Rapid prototyping of MCP servers
  • Learning MCP protocol best practices
  • Automating repetitive server setup
  • Creating custom integrations quickly

Location: mcp-generator/

Documentation: See mcp-generator/README.md for detailed usage instructions.

2. GitHub MCP Server

Connect your AI assistant directly to GitHub for repository management, issue tracking, and code collaboration.

Capabilities:

  • 📦 Create, update, and manage repositories
  • 🔍 Search code, issues, and users
  • 📝 Create and manage issues and pull requests
  • 🌿 Branch management and file operations
  • 👥 Repository collaboration features
  • 📊 Access repository statistics and insights

Package: @modelcontextprotocol/server-github

3. Calculator Server (Example)

A demonstration MCP server generated by MCP Generator, showcasing basic mathematical operations.

Capabilities:

  • ➕ Addition and subtraction
  • ✖️ Multiplication and division
  • 📊 Power operations

Location: test-output/calculator-server/ (generated example)

Coming Soon:

You can now generate these yourself using MCP Generator!

  • Filesystem MCP Server - Local file system access
  • Database MCP Server - SQL database integration
  • API MCP Server - Custom REST API connections
  • Cloud Storage MCP Server - S3, GCS, Azure Blob integration
  • Custom Servers - Use MCP Generator to create any server you need!

📦 Installation

Prerequisites

  • Python 3.10+ (for MCP Generator and Python-based servers)
  • Node.js (v18 or higher) (for GitHub MCP server)
  • npm or yarn (for GitHub MCP server)
  • An AI development tool that supports MCP (e.g., Cursor, Claude Code)
  • GitHub Personal Access Token (for GitHub MCP server)

Setup Steps

  1. Clone this repository:

    git clone https://github.com/Ahmet-Ruchan/MCP.git
    cd MCP
    
  2. Install MCP Generator (recommended):

    cd mcp-generator
    pip install -r requirements.txt
    cd ..
    
  3. Get your GitHub Personal Access Token (for GitHub server):

    • Go to GitHub Settings → Developer settings → Personal access tokens → Tokens (classic)
    • Generate new token with required scopes: repo, read:user, user:email
    • Copy the token for configuration
  4. Configure MCP in Cursor/Claude Code:

    Edit or create ~/.cursor/mcp.json or ~/.config/claude-code/mcp.json:

    {
      "mcpServers": {
        "mcp-generator": {
          "command": "python",
          "args": [
            "/absolute/path/to/MCP/mcp-generator/server.py"
          ]
        },
        "github": {
          "command": "npx",
          "args": [
            "-y",
            "@modelcontextprotocol/server-github"
          ],
          "env": {
            "GITHUB_PERSONAL_ACCESS_TOKEN": "your_github_token_here"
          }
        }
      }
    }
    

    Note: Replace /absolute/path/to/MCP with the actual path where you cloned this repository.

  5. Clear npx cache (if needed for GitHub server):

    rm -rf ~/.npm/_npx
    
  6. Restart Cursor/Claude Code

⚙️ Configuration

GitHub MCP Server Configuration

{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_your_token_here"
      }
    }
  }
}

Important Notes:

  • ⚠️ Never commit your actual token to version control
  • ⚠️ Remove < and > brackets from token - use raw token value only
  • ⚠️ Ensure token has appropriate permissions for intended operations

Environment Variables

| Variable | Description | Required | |----------|-------------|----------| | GITHUB_PERSONAL_ACCESS_TOKEN | GitHub PAT for API access | Yes |

🎯 Usage Examples

Using MCP Generator

Example 1: Generate a Calculator Server

// Ask your AI assistant:
"Use the mcp-generator to create a calculator server with add, subtract, multiply, and divide tools"

// The generator will:
// 1. Create a complete server structure
// 2. Generate all necessary files
// 3. Provide installation instructions

Example 2: Generate a Weather API Server

// Ask your AI assistant:
"Generate a full MCP server for weather data with a search tool, current weather resource, and a forecast analysis prompt"

Example 3: Validate Before Generating

// Ask your AI assistant:
"Validate this MCP config before generating: {your config here}"

Using GitHub MCP Server

Example 4: Create a Repository

// Using MCP in Cursor, you can ask:
"Create a new GitHub repository called 'my-awesome-project' with a description"

Example 5: Search Repositories

// Find repositories:
"Search for my repositories related to machine learning"

Example 6: Manage Issues

// Create and manage issues:
"Create an issue in my repository about adding authentication"

Example 7: Push Files

// Push files to repository:
"Push these files to my GitHub repository"

🐛 Troubleshooting

Common Issues

1. "ERR_MODULE_NOT_FOUND" Error

# Solution: Clear npx cache
rm -rf ~/.npm/_npx

2. "Bad credentials" Error

  • Check if token is correct and properly formatted (no <> brackets)
  • Verify token has required permissions
  • Regenerate token if expired

3. "No server info found" Error

  • Restart Cursor completely
  • Check mcp.json syntax
  • Verify command and args are correct

4. Package Deprecated Warning

npm warn deprecated @modelcontextprotocol/server-github
  • This is expected - the package works but may have newer alternatives
  • Continue using unless critical issues arise

Debug Mode

To see detailed MCP logs in Cursor:

  1. Open Cursor logs: Help → Show Logs
  2. Look for MCP-related entries
  3. Check for connection and authentication issues

🤝 Contributing

Contributions are welcome! Feel free to:

  • 🐛 Report bugs
  • 💡 Suggest new MCP server integrations
  • 📝 Improve documentation
  • 🔧 Submit pull requests

How to Contribute

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/AmazingFeature)
  3. Commit your changes (git commit -m 'Add some AmazingFeature')
  4. Push to the branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

📚 Resources

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

  • Anthropic for developing the MCP protocol
  • Cursor for MCP integration support
  • The open-source community for MCP server implementations

📞 Contact

Ahmet Ruçhan Avcı


⭐ If you find this repository helpful, please consider giving it a star!

Made with ❤️ using MCP

Quick Setup
Installation guide for this server

Install Package (if required)

uvx mcp

Cursor configuration (mcp.json)

{ "mcpServers": { "ahmet-ruchan-mcp": { "command": "uvx", "args": [ "mcp" ] } } }