Mallory MCP Server

Mallory provides a robust source of cyber and threat intelligence. Use this MCP Server to enable your agents with real-time cyber threat intelligence and detailed information about vulnerabilities, threat actors, malware, techniques and other cyber-relevant entities and content.

📋 Prerequisites

Python 3.13 or higher
uv for dependency management (recommended)

🚀 Quick Start

Installation

Clone the repository:

git clone https://github.com/malloryai/mallory-mcp-server.git
cd mallory-mcp-server

Set up a virtual environment and install dependencies:

# Using uv (recommended)
uv venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv pip install -e .

# Or using pip
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -e .

Install Development Dependencies

For development work, install the optional dependencies:

# Using uv
uv pip install -e ".[lint,tools]"

# Or using pip
pip install -e ".[lint,tools]"

Set Up Pre-commit Hooks

This project uses pre-commit hooks to ensure code quality. Install them with:

pre-commit install
./scripts/install-commit-hook.sh

⚙️ Configuration

Create a .env file in the project root with the following variables:

APP_ENV=local
MALLORY_API_KEY=your_api_key_here

🏃‍♂️ Running the Server

Direct Execution

python -m malloryai.mcp.app

uv run malloryai/mcp/app.py

Via the Claude Desktop Configuration

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "MalloryAI": {
      "command": "/path/to/uv",
      "args": [
        "run",
        "--python",
        "/path/to/mcp-server/.venv/bin/python",
        "/path/to/mcp-server/malloryai/mcp/app.py"
      ],
      "env": {
        "MALLORY_API_KEY": "your_api_key_here"
      }
    }
  }
}

📦 Project Structure

.
├── README.md
├── app.py                  # Main application entry point
├── malloryai/              # Main package
│   ├── __init__.py
│   └── mcp/                # MCP subpackage
│       ├── __init__.py
│       ├── config/         # Configuration modules
│       ├── server/         # Server implementation
│       ├── tools/          # Tool implementations
│       └── utils/          # Utility functions
├── pyproject.toml          # Project metadata and dependencies
├── scripts/                # Utility scripts
│   └── install-commit-hook.sh

🧪 Development

Code Style

This project uses:

Black for code formatting
isort for import sorting
flake8 for linting

Format your code with:

black .
isort .
flake8

Commit Message Format

This project follows the conventional commit format. Each commit message should follow this pattern:

<type>[(scope)]: <description>

Where type is one of:

feat or feature: New feature
fix, bugfix, or hotfix: Bug fixes
chore: Regular maintenance tasks
refactor: Code changes that neither fix bugs nor add features
docs: Documentation only changes
style: Changes that don't affect the meaning of the code
test: Adding or correcting tests
perf: Performance improvements
ci: Changes to CI configuration
build: Changes to build system or dependencies
revert: Reverting previous commits

Example: feat(server): add new authentication method

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Fork the repository
Create your feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'feat: add some amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request