Law Scrapper MCP 📜⚖️

A comprehensive Model Context Protocol (MCP) server for accessing and analyzing Polish legal acts from the Sejm API, enabling AI-powered legal research and document analysis.

✨ Features

• Comprehensive legal act access - Full access to Polish legal acts from Dziennik Ustaw and Monitor Polski
• Advanced search & filtering - Multi-criteria search by date, type, keywords, publisher, and status
• Detailed document analysis - Complete metadata, structure, references, and content retrieval
• Date & time utilities - Specialized date calculations for legal document analysis
• System metadata access - Keywords, statuses, document types, and institution data
• FastMCP integration - Built with FastMCP framework following best practices
• SSE transport - Server-Sent Events for reliable real-time communication
• Professional documentation - Extensive examples and clear parameter descriptions
• RESTful API integration - Direct connection to official Sejm API endpoints

📋 Requirements / prerequisites

• Python: 3.12 or higher
• Package manager: uv (recommended) or pip
• Internet connection: Required for accessing Sejm API endpoints
• MCP-compatible tool: Cursor IDE, Claude Code, or other MCP-supported applications

🚀 Installation

Using uv (recommended)

# Clone the repository
git clone https://github.com/numikel/law-scrapper-mcp.git
cd law-scrapper-mcp

# Install dependencies
uv sync

Using pip

# Clone the repository
git clone https://github.com/numikel/law-scrapper-mcp.git
cd law-scrapper-mcp

# Install dependencies
pip install -e .

Using uvx (no installation required)

For quick testing or development without cloning the repository:

# Run the server directly from GitHub
uvx --from git+https://github.com/numikel/law-scrapper-mcp law-scrapper

This will download and run the server with SSE transport on port 7683.

⚙️ Configuration

MCP server configuration

This server uses Server-Sent Events (SSE) transport for better performance and reliability. The server runs on http://localhost:7683/sse and provides real-time communication with MCP clients.

Important notes:

• Make sure port 7683 is available before starting the server
• The server must be running before connecting MCP clients
• SSE provides better error handling and connection management than STDIO

Add the following configuration to your MCP client's configuration file:

For Cursor IDE (.cursor/mcp.json):

{
  "mcpServers": {
    "law-scrapper-mcp": {
      "url": "http://localhost:7683/sse",
      "transport": "sse"
    }
  }
}

For Claude Code:

claude mcp add law-scrapper-mcp uvx '--from' 'git+https://github.com/numikel/law-scrapper-mcp' 'law-scrapper'

Note: Claude Code will run the server process automatically. The server uses SSE transport and runs on port 7683

For other MCP tools (.mcp.json or mcp_config.json):

{
  "mcpServers": {
    "law-scrapper-mcp": {
      "url": "http://localhost:7683/sse",
      "transport": "sse"
    }
  }
}

🎯 Quick start / usage

Once configured, you can start using the legal research tools:

Basic usage examples

Get current date for legal analysis:

"What is today's date?"

Search for specific legal acts:

"Find all regulations from 2020 containing 'environment'"

Analyze document structure:

"Show me the table of contents for act DU/2020/1"

Get comprehensive document details:

"Give me full information about legal act DU/2020/1280"

Available tool categories

The server provides 14 specialized tools organized in 4 categories:

🕒 Dates & time (2 tools)

• get_current_date - Get current date for legal analysis
• calculate_date_offset - Calculate date ranges for legal periods

📚 System metadata (6 tools)

• get_legal_keywords - Access all available search keywords
• get_legal_publishers - List all legal publishers (DU, MP)
• get_publisher_details - Detailed publisher information
• get_legal_statuses - Document status types
• get_legal_types - Legal document types
• get_legal_institutions - Involved institutions

🔍 Acts browsing & search (2 tools)

• search_legal_acts - Advanced multi-criteria search
• get_publisher_year_acts - Browse acts by publisher and year

📋 Act details & analysis (4 tools)

• get_act_comprehensive_details - Complete document metadata
• get_act_content - PDF/HTML content retrieval
• get_act_table_of_contents - Document structure analysis
• get_act_relationships - Legal references and amendments

📁 Project structure

law-scrapper-mcp/
├── app.py                    # Main MCP server implementation with 14 legal research tools
├── pyproject.toml           # Project configuration, dependencies, and CLI scripts
├── uv.lock                  # Lock file ensuring reproducible builds
├── README.md               # Project documentation
└── __pycache__/            # Python bytecode cache (generated)

🛠️ Development

Development setup

# Install in development mode
uv sync

# Run the server directly (SSE transport on port 7683)
uv run app.py

# Or use the installed script
law-scrapper

# Or run directly with uvx (from local directory)
uvx . --python python

Server information:

• Transport: Server-Sent Events (SSE)
• Host: 0.0.0.0 (accessible from any network interface)
• Port: 7683
• Endpoint: http://localhost:7683/sse

Running tests

# Run basic functionality tests
uv run python -c "
import app
print('Server imports successfully')
funcs = [name for name in dir(app) if name.startswith('get_')]
print(f'Available tools: {len(funcs)}')
"

Code quality

The project follows FastMCP best practices:

• Tagged Tools: All tools have descriptive tags for filtering
• Annotated Parameters: Every parameter has clear descriptions
• Comprehensive Examples: Minimum 5 examples per tool
• Professional Documentation: Detailed docstrings and usage examples

🤝 Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes using Conventional Commits format
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

Development guidelines

• Follow FastMCP best practices for tool definitions
• Include comprehensive examples and parameter descriptions
• Add appropriate tags for tool categorization
• Test all new functionality before submitting
• Use English for all code comments and documentation

📄 License

This project is licensed under the MIT License

👤 Author

@numikel

Legal disclaimer: This tool provides access to Polish legal documents for research purposes. Always consult with qualified legal professionals for legal advice and interpretation of laws.