Yogosha MCP

🚀 Yogosha MCP Server

This project seamlessly connects the Yogosha Bug Bounty Platform with the Model Context Protocol (MCP) ecosystem, allowing for programmatic interaction with Yogosha resources.

🚀 Quick Start

Once the server is up and running, you can use Claude Desktop or any MCP client to perform operations such as listing all programs, creating new assets, and patching vulnerabilities. For example:

• List all programs: list_programs()
• Create a new asset: create_asset(program_id, asset_data)
• Patch a vulnerability: patch_vulnerability(program_id, vulnerability_id, patch_data)

✨ Features

• Automation: Automate vulnerability management, asset inventory, reporting, etc., using natural language or workflow tools.
• Integration: Connect Yogosha with any MCP - compatible agent, LLM, or workflow orchestrator.
• Security: Enforce API key management via environment variables, with all operations being stateless and auditable.
• Extensibility: Add new endpoints or custom logic by extending server.py without modifying the core infrastructure.
• Productivity: Significantly reduce the time for triaging, updating, or reporting on vulnerabilities and assets.

📦 Installation

Requirements

• Python 3.8+
• uv (for fast Python package management and running)
• Yogosha API Key

Steps

1. Install dependencies:

   uv pip install -r requirements.txt
   

2. Set your Yogosha API key:

   export YOGOSHA_API_KEY=your_yogosha_api_key_here
   

3. Run the MCP server:

   uv run server.py
   

   The server uses stdio transport by default for integration with Claude Desktop and other MCP clients.

💻 Usage Examples

Basic Usage

Once the server is running, use the following commands in Claude Desktop or other MCP clients:

# List all programs
list_programs()
# Create a new asset
create_asset(program_id, asset_data)
# Patch a vulnerability
patch_vulnerability(program_id, vulnerability_id, patch_data)

📚 Documentation

What Problems Does This Solve?

• Manual API Work: Eliminate the need to write custom scripts for each Yogosha API call. Just use the MCP tool interface.
• AI Copilot Enablement: Allow LLMs and automation agents to directly manage your bug bounty program, assets, and reports.
• Unified Security Operations: Integrate Yogosha with other security tools and dashboards using the MCP standard.

MCP Server Configuration for Claude Desktop

To use this server with Claude Desktop, add the following to your mcpserver.json:

{
  "mcpServers": {
    "YogoshaMCP": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/haji/mcp - servers/yogosha - mcp",
        "run",
        "server.py"
      ]
    }
  }
}

• Adjust the --directory path if your project is in a different location.
• The server will be available as "YogoshaMCP" in Claude Desktop.

🔧 Technical Details

Security

• The API key is read from the YOGOSHA_API_KEY environment variable. Never commit your API key to source control.
• All code is designed to be stateless and safe for use as MCP tools.

Extending

• To add more endpoints, follow the function pattern in server.py.

📄 License

MIT or as specified in this repository.