Washington Law MCP Server

Washington Law MCP Server

Provides offline access to Washington State's Revised Code of Washington (RCW) and Washington Administrative Code (WAC) for AI agents. Enables fast retrieval, full-text search, and navigation of all Washington state laws through natural language queries.

Category
Visit Server

README

Washington Law MCP Server

An MCP (Model Context Protocol) server that provides offline access to Washington State's Revised Code of Washington (RCW) and Washington Administrative Code (WAC) for AI agents.

Features

  • Completely Offline: All law texts are stored locally in SQLite database
  • Fast Access: Instant retrieval of any RCW or WAC section
  • Full-Text Search: Search across all Washington laws using SQLite FTS5
  • Comprehensive Coverage: Access to all RCW titles, chapters, and sections
  • MCP Compatible: Works with any MCP-compatible AI client (Claude, etc.)

Architecture

The project consists of two main components:

  1. Data Collection Phase (one-time setup): Scrapers that download all RCW/WAC texts
  2. MCP Server (runtime): Serves law texts from local database with no external calls

Installation

# Clone the repository
git clone <repository-url>
cd law_rule_mcp

# Install dependencies
npm install

# Initialize the database
npm run init:db

# Scrape RCW data (this will take several hours)
npm run scrape:rcw

# Build the TypeScript code
npm run build

Usage

Running the MCP Server

npm start

Testing with MCP Inspector

npm test

Configuring with Claude Desktop

Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "washington-law": {
      "command": "node",
      "args": ["/path/to/law_rule_mcp/dist/index.js"]
    }
  }
}

Available MCP Tools

get_rcw

Retrieve the full text of a specific RCW section.

  • Parameters:
    • citation (string): RCW citation (e.g., "46.61.502")

get_wac

Retrieve the full text of a specific WAC section.

  • Parameters:
    • citation (string): WAC citation (e.g., "296-24-12005")

search_laws

Search Washington laws by keywords or phrases.

  • Parameters:
    • query (string): Search terms
    • limit (number, optional): Max results (default: 20)

list_rcw_titles

List all RCW titles with section counts.

list_rcw_chapters

List all chapters within a specific RCW title.

  • Parameters:
    • titleNum (string): Title number (e.g., "46")

list_rcw_sections

List all sections within a specific RCW chapter.

  • Parameters:
    • chapterNum (string): Chapter number (e.g., "46.61")

get_statistics

Get database statistics including section counts and last update time.

Project Structure

law_rule_mcp/
├── src/
│   ├── index.ts              # MCP server entry point
│   ├── database/
│   │   ├── init.ts          # Database initialization
│   │   └── database.ts      # Database access layer
│   ├── scraper/
│   │   └── rcw-scraper.ts   # RCW web scraper
│   └── types.ts             # TypeScript type definitions
├── data/
│   └── washington-laws.db   # SQLite database (created after scraping)
├── package.json
├── tsconfig.json
└── README.md

Database Schema

The SQLite database contains:

  • rcw table: Full text and metadata for all RCW sections
  • wac table: Full text and metadata for all WAC sections
  • rcw_fts / wac_fts: Full-text search indexes
  • metadata table: Database version and update timestamps
  • scraper_progress table: Tracks scraping progress

Updating the Database

To update the law database with the latest changes:

# Re-run the scraper to fetch updated laws
npm run scrape:rcw

The scraper will update existing sections and add new ones.

Development

# Watch mode for development
npm run dev

# Build TypeScript
npm run build

# Test with MCP inspector
npm test

Notes

  • Initial scraping takes several hours due to rate limiting (respectful crawling)
  • Database size is approximately 200-500 MB after compression
  • The server operates completely offline once data is scraped
  • All database queries are read-only during MCP server operation

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured