EGH Research MCP Server
Provides offline research and advanced search capabilities for Ellen Gould Harmon's writings via MCP and HTTP APIs, including PDF generation and Docker deployment.
README
EGH Research
Complete offline research platform for Ellen Gould Harmon's writings with PDF generation and Docker deployment
š Quick Start with Docker
The fastest way to get started is with our pre-built Docker image:
# Pull and run the latest image
docker pull ghcr.io/gospelsounders/egw-writings-mcp/egh-research-server:latest
docker run -p 3000:3000 ghcr.io/gospelsounders/egw-writings-mcp/egh-research-server:latest
# Test the API
curl http://localhost:3000/health
curl http://localhost:3000/api/docs
š Live API Documentation | š Full Documentation
š Overview
EGH Research is a comprehensive platform for offline research of Ellen Gould Harmon's writings, providing both Model Context Protocol (MCP) and HTTP REST API access with advanced PDF generation capabilities.
Key Components
- š EGH Research Server: Dual-protocol server (MCP + HTTP API) with offline database
- š„ Content Downloader: Bulk data extraction and database population tools
- š Web Interface: Modern React-based research platform
- š³ Docker Deployment: Production-ready containerization with GitHub Actions
Core Features
- ā” Offline Operation: Complete independence from external services
- š Advanced Search: FTS5 full-text search with sub-millisecond response times
- š PDF Generation: On-demand PDF creation with customizable formatting
- š Dual APIs: Both MCP and REST APIs for maximum compatibility
- š³ Docker Ready: Multi-architecture containers (AMD64, ARM64)
- š± Modern UI: Responsive web interface for research
š¦ Architecture
āāā apps/
ā āāā local-server/ # Main EGH Research Server (MCP + HTTP API)
ā āāā downloader/ # Data extraction and database tools
ā āāā api-server/ # Live API integration server
ā āāā website/ # React-based research interface
āāā packages/
ā āāā shared/ # Common utilities and database management
ā āāā egw-pdf-generator/ # PDF generation engine
āāā .github/workflows/ # CI/CD with Docker builds
š Installation Options
Option 1: Docker (Recommended)
# Using Docker Run
docker pull ghcr.io/gospelsounders/egw-writings-mcp/egh-research-server:latest
docker run -p 3000:3000 ghcr.io/gospelsounders/egw-writings-mcp/egh-research-server:latest
# Using Docker Compose
curl -O https://raw.githubusercontent.com/GospelSounders/egw-writings-mcp/master/apps/local-server/docker-compose.yml
docker-compose up -d
Option 2: Global NPM Installation
# Install the research server
npm install -g @surgbc/egw-research-server
# Install supporting tools
npm install -g @surgbc/egw-writings-downloader
# Start the server
egw-research-server --http --port 3000
Option 3: Local Development
# Clone and setup
git clone https://github.com/surgbc/egh-research.git
cd egh-research
pnpm install && pnpm build
# Start HTTP server
cd apps/local-server
npm run start:http
# Or start MCP server
npm run start:mcp
š§ Configuration
Environment Variables
NODE_ENV: Development/production modeLOG_LEVEL: Logging verbosity (debug, info, warn, error)PDF_CLEANUP_INTERVAL: PDF file cleanup frequency
MCP Client Configuration
{
"mcpServers": {
"egh-research": {
"command": "egw-research-server"
}
}
}
Database Setup
# Download sample data
npx @surgbc/egw-writings-downloader quick-start --zip
# Or use the Make target (development)
make egw-quick-start
š API Reference
HTTP REST API
# Health and status
GET /health
GET /api/docs
GET /stats
# Content access
GET /content/books?page=1&limit=50&lang=en
GET /content/books/{id}
GET /content/books/{id}/toc
GET /search?q=righteousness&limit=20
# PDF generation
POST /content/books/{id}/generate-pdf
GET /pdf/status/{token}
GET /pdf/download/{token}
MCP Tools
search_local- Full-text search with FTS5 highlightingget_local_book- Book information and metadataget_local_content- Chapter and paragraph contentlist_local_books- Paginated book listingsbrowse_by_reference- Navigation by EGW reference codesget_context- Contextual paragraph retrievalget_database_stats- Database metrics and statistics
š Complete API Documentation
š³ Docker & Production
Production Deployment
# Pull latest production image
docker pull ghcr.io/surgbc/egh-research-server:latest
# Run with persistent storage and health checks
docker run -d \
--name egh-research \
-p 3000:3000 \
-v egh-data:/app/apps/local-server/data \
--restart unless-stopped \
--health-cmd="curl -f http://localhost:3000/health || exit 1" \
--health-interval=30s \
ghcr.io/surgbc/egh-research-server:latest
Build from Source
# Build local image
./scripts/build-docker.sh --tag local
# Build with custom registry
./scripts/build-docker.sh --registry ghcr.io/yourname --tag v1.0.0
GitHub Actions
The project includes comprehensive CI/CD workflows:
- šØ Build & Test: Automated testing and building on push/PR
- š³ Docker Build: Multi-architecture container builds
- š Security Scan: Vulnerability scanning with Trivy
- š Documentation: Auto-deployment to GitHub Pages
- š Release: Automated releases with Docker publishing
š Performance & Capabilities
Search Performance
- Sub-millisecond search response times
- FTS5 full-text search with ranking
- Highlighted search results with context
- Reference navigation (e.g., "AA 15.1", "DA 123")
PDF Generation
- Customizable formatting: Page size, fonts, margins
- Table of contents: Automatic generation with configurable depth
- Background processing: Non-blocking PDF generation
- Progress tracking: Real-time generation status
- Automatic cleanup: Scheduled file cleanup
Database Features
- SQLite with FTS5 full-text search
- Efficient storage with reference indexing
- Multi-language support (150+ languages)
- Offline operation - no internet required after setup
šÆ Use Cases
Research Applications
- Academic research on Ellen Gould Harmon's writings
- Topic compilation across multiple books
- Reference verification and cross-referencing
- Contextual analysis with surrounding paragraphs
Educational Use
- Classroom instruction with offline access
- Student research projects with PDF generation
- Study materials creation with custom formatting
- Reference lookup during presentations
Technical Integration
- MCP clients (Claude, etc.) for AI-assisted research
- REST API integration for custom applications
- Docker deployment for institutional use
- Batch processing for large-scale analysis
š¤ Contributing
We welcome contributions! Here's how to get started:
Development Workflow
- Fork the repository
- Create a feature branch from
main - Make your changes with tests
- Run
pnpm lint && pnpm build && pnpm test - Submit a pull request
Development Commands
# Setup development environment
pnpm install
pnpm build
# Run tests and linting
pnpm test
pnpm lint
# Start development servers
pnpm dev # All packages in watch mode
pnpm --filter local-server dev # Just the research server
pnpm --filter website dev # Just the web interface
# Build for production
pnpm build
# Docker development
./scripts/build-docker.sh --tag dev
docker run -p 3000:3000 egh-research-server:dev
š Educational and Research Use
This platform is designed specifically for educational and research purposes related to Ellen Gould Harmon's writings. The software:
- Respects intellectual property rights and fair use guidelines
- Provides tools for legitimate academic research
- Enables offline access for educational institutions
- Supports citation and reference verification
Key Benefits for Researchers
- Complete offline access - No dependency on external services
- Advanced search capabilities - Find specific passages quickly
- PDF generation - Create formatted documents for study
- Reference cross-linking - Navigate between related content
- Context preservation - Maintain surrounding content for accuracy
Academic Citation
When using this software in academic work, please cite:
EGH Research Platform. (2024).
Offline research platform for Ellen Gould Harmon's writings.
GitHub: https://github.com/surgbc/egh-research
š Security & Privacy
- No data collection: All processing happens locally
- Open source: Fully auditable codebase
- Security scanning: Automated vulnerability detection
- Container security: Non-root user and minimal attack surface
š License
MIT License - Open source software for educational and research use.
See LICENSE for full terms.
šāāļø Support
- š Documentation: https://surgbc.github.io/egh-research/
- š Issues: GitHub Issues
- š¬ Discussions: GitHub Discussions
- š§ Email: Contact maintainers for security issues
Developed by surgbc ⢠Built with ā¤ļø for educational and research purposes
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.