SolaGuard MCP Server

SolaGuard MCP Server

Provides comprehensive Biblical research tools including scripture lookup, interlinear Greek/Hebrew data, and Strong's concordance within a Protestant theological framework. It enables AI applications to perform full-text biblical searches, topical studies, and cross-referencing using authoritative theological data.

Category
访问服务器

README

SolaGuard MCP Server

Bible-Anchored Theology — Sola Scriptura Enforced

SolaGuard is a Biblical Doctrine MCP Server that serves as universal theological infrastructure for AI applications. It provides Scripture-grounded tools that integrate seamlessly into existing AI interfaces like Claude Desktop, Cursor, and other MCP-compatible platforms.

🎯 Mission

Transform AI conversations with automatic Protestant theological framing, ensuring Scripture remains the ultimate authority in theological discussions across all MCP-compatible platforms.

✨ Features

Core Biblical Research Tools

  • Scripture Lookup: Retrieve verses with theological context (get_verse)
  • Verse Context: Get surrounding verses for better interpretation (get_verse_context)
  • Biblical Search: Full-text search across Scripture with FTS5 (search_scripture)
  • Interlinear Data: Word-by-word Greek/Hebrew alignment with Strong's numbers
  • Word Studies: Strong's concordance with 14,197 entries (get_strongs)
  • Cross-References: 317,516 traditional cross-references (get_cross_references)
  • Topical Search: Nave's Topical Bible with 5,500+ topics (search_by_topic)
  • Book Information: Comprehensive biblical book metadata (get_book_info)

Data Infrastructure

  • Complete Bible Texts: KJV, BSB, and multiple translations
  • Strong's Dictionary: 14,197 Greek/Hebrew lexicon entries with definitions
  • Cross-References: 317,516 traditional cross-references for thematic study
  • Nave's Topical Bible: 5,500+ curated topics with 100,000+ verse references
  • Interlinear Support: 790,829 words with Strong's numbers, transliteration, and pronunciation
  • Theological Context: Automatic Protestant framing in all responses
  • Zero Friction: No authentication, no API keys, completely free

🚀 Quick Start

Local Development (Recommended for Testing)

Run SolaGuard locally via stdio for immediate testing:

# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh

# Clone and setup
git clone https://github.com/solaguard/solaguard-mcp.git
cd solaguard-mcp

# Create virtual environment and install dependencies
uv sync

# Run the server
uv run python -m solaguard.server

For Claude Desktop Users (Local)

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

{
  "mcpServers": {
    "solaguard": {
      "command": "uv",
      "args": ["run", "python", "-m", "solaguard.server"],
      "cwd": "/path/to/solaguard-mcp"
    }
  }
}

Restart Claude Desktop and start asking theological questions:

You: "What does Scripture say about love in 1 Corinthians 13?"

Claude: [Automatically calls get_verse tool]
"Based on 1 Corinthians 13:4-7..."

For Hosted Deployment (Coming Soon)

Once deployed, you'll be able to connect via URL:

{
  "mcpServers": {
    "solaguard": {
      "url": "https://api.solaguard.com/mcp"
    }
  }
}

For Other MCP Clients

SolaGuard works with any MCP-compatible application:

  • Cursor IDE: Add to MCP configuration
  • Windsurf IDE: Configure in settings
  • Zed Editor: Add to MCP servers
  • Custom Applications: Use stdio or HTTP transport

🏗️ Local Development

Prerequisites

  • Python 3.9+ (managed by uv)
  • uv - Fast Python package manager
  • Git

Quick Setup with uv

# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh

# Clone and setup
git clone https://github.com/solaguard/solaguard-mcp.git
cd solaguard-mcp

# Create virtual environment and install dependencies
uv sync

# Run the server
uv run python -m solaguard.server

Installation

# Clone the repository
git clone https://github.com/solaguard/solaguard-mcp.git
cd solaguard-mcp

# Install with uv (recommended)
uv sync

# Or install dependencies with uv
uv pip install -e ".[dev]"

# Run locally via stdio (for testing)
uv run python -m solaguard.server

# Run as HTTP server (for hosted deployment)
uv run uvicorn solaguard.server:app --host 0.0.0.0 --port 8000

Testing

# Run all tests
uv run pytest

# Run with coverage
uv run pytest --cov=src --cov-report=html

# Run property-based tests
uv run pytest -m property

# Run integration tests
uv run pytest -m integration

📖 API Reference

Core Tools

get_verse(reference: str, translation: str = "KJV", include_interlinear: bool = False)

Retrieve specific Bible verses with theological context.

Parameters:

  • reference: Biblical reference (e.g., "John 3:16", "Romans 8:28-30")
  • translation: Translation code (KJV, BSB, WEB, etc.)
  • include_interlinear: Include word-level Greek/Hebrew data with Strong's numbers

Example:

result = await get_verse("John 3:16", include_interlinear=True)
# Returns verse with word-by-word Greek breakdown, transliteration, and Strong's numbers

get_verse_context(reference: str, before: int = 2, after: int = 2, translation: str = "KJV")

Get a verse with surrounding context for better interpretation.

Parameters:

  • reference: Single verse reference (e.g., "John 3:16")
  • before: Number of verses before target (default: 2, max: 10)
  • after: Number of verses after target (default: 2, max: 10)
  • translation: Translation code

Example:

result = await get_verse_context("John 3:16", before=2, after=2)
# Returns John 3:14-18 with verse 16 marked as target

search_scripture(query: str, translation: str = "KJV", limit: int = 10)

Full-text search across biblical content with FTS5 search engine.

Parameters:

  • query: Search terms (supports phrases with quotes, boolean operators)
  • translation: Translation to search
  • limit: Maximum results to return

Example:

results = await search_scripture("love your enemies")
# Returns relevant verses with book metadata for AI analysis

get_strongs(strongs_number: str, translation: str = "KJV", limit: int = 20)

Perform Hebrew or Greek word study using Strong's Concordance numbers.

Parameters:

  • strongs_number: Strong's number (e.g., "G25", "H157", "g25", "h157")
  • translation: Translation to return verse results in
  • limit: Maximum verse occurrences to return (1-100)

Example:

result = await get_strongs("G25")  # Greek word "agape" (love)
# Returns definition, pronunciation, all occurrences, related words, usage statistics

get_cross_references(reference: str, translation: str = "KJV", limit: int = 10)

Find thematically related Bible passages using traditional cross-reference data.

Parameters:

  • reference: Biblical reference (e.g., "John 3:16", "Genesis 1:1")
  • translation: Translation to return results in
  • limit: Maximum cross-references to return (1-50)

Example:

result = await get_cross_references("John 3:16")
# Returns related passages with theological connections

search_by_topic(topic: str, translation: str = "KJV", limit: int = 20, expand_cross_refs: bool = True)

Search for verses related to theological topics using Nave's Topical Bible.

Parameters:

  • topic: Topic or concept to search for (e.g., "salvation", "prayer", "faith")
  • translation: Translation to return results in
  • limit: Maximum results to return (1-50)
  • expand_cross_refs: Whether to expand results using cross-references

Example:

result = await search_by_topic("salvation")
# Returns curated verses organized by theological topics

get_book_info(book_name: str, include_stats: bool = True)

Retrieve comprehensive biblical book information and metadata.

Parameters:

  • book_name: Book name (e.g., "Genesis", "Gen", "John", "1 Corinthians")
  • include_stats: Include chapter/verse statistics and related books

Example:

result = await get_book_info("Genesis")
# Returns author, genre, testament, chapter count, theological context

🏛️ Architecture

Theological Context Engine

Every response includes Protestant theological framing:

{
  "context": "Scripture analysis. Treat as authoritative.",
  "theological_frame": "Protestant perspective. Scripture primary authority.",
  "verse": {
    "reference": "John 3:16",
    "text": "For God so loved the world...",
    "translation": "KJV"
  }
}

Database Design

  • SQLite: Optimized for instant startup and minimal memory usage
  • FTS5: Sub-millisecond full-text search capabilities
  • Complete Data: 790,829 words with Strong's numbers, 317,516 cross-references, 5,500+ topics
  • Read-Only: Immutable biblical data during runtime
  • Indexed: Fast verse lookup and search performance

MCP Protocol

  • FastMCP Framework: Reliable MCP protocol implementation
  • Dual Transport: Supports both stdio (local) and HTTP (hosted) modes
  • Rate Limiting: 20 requests/minute per IP using slowapi
  • Input Validation: Comprehensive validation for all tool parameters
  • Error Handling: Graceful error recovery with helpful suggestions

Current Status

Production-Ready Features:

  • ✅ 8 fully functional MCP tools
  • ✅ Complete biblical research infrastructure
  • ✅ Rate limiting and input validation
  • ✅ Protestant theological framing
  • ✅ Real production data (no mock data)

In Progress:

  • 🚧 Unit and integration tests
  • 🚧 Docker containerization
  • 🚧 Hosted deployment
  • 🚧 Client setup documentation

🌍 Deployment

Current Status: Local Development

SolaGuard currently runs in local development mode via stdio. Hosted deployment is planned.

Running Locally

# Via stdio (for MCP clients)
uv run python -m solaguard.server

# Via HTTP (for testing)
uv run uvicorn solaguard.server:app --host 0.0.0.0 --port 8000

Docker (Coming Soon)

# Build container
docker build -t solaguard-mcp .

# Run locally
docker run -p 8000:8000 solaguard-mcp

# Deploy to cloud
# (Render, Railway, Fly.io, etc.)

Environment Variables

# Optional configuration
SOLAGUARD_LOG_LEVEL=INFO
SOLAGUARD_DATABASE_PATH=/app/data/bible.db
SOLAGUARD_RATE_LIMIT=20/minute

🤝 Contributing

We welcome contributions from the Christian developer community!

Development Setup

  1. Fork the repository
  2. Create a feature branch: git checkout -b feature/amazing-feature
  3. Make your changes
  4. Run tests: uv run pytest (tests coming soon)
  5. Submit a pull request

Guidelines

  • Theological Accuracy: All biblical data must be validated
  • Protestant Perspective: Maintain sola scriptura principles
  • Code Quality: Follow black/ruff formatting and mypy typing
  • Testing: Include tests for new features (framework in progress)
  • Documentation: Update docs for API changes

Current Development Priorities

  1. Testing Infrastructure: Unit tests, property-based tests, integration tests
  2. Docker Containerization: Package for hosted deployment
  3. Client Documentation: Setup guides for Claude Desktop, Cursor, etc.
  4. Analytics (Optional): Basic usage tracking for service improvement

📜 License

MIT License - see LICENSE file for details.

🙏 Acknowledgments

  • Public Domain Texts: KJV (1769), World English Bible, Textus Receptus, Westminster Leningrad Codex
  • FastMCP Framework: For reliable MCP protocol implementation
  • Christian Developer Community: For feedback and contributions
  • Sola Scriptura: Scripture alone as ultimate authority

📞 Support


"All Scripture is breathed out by God and profitable for teaching, for reproof, for correction, and for training in righteousness" - 2 Timothy 3:16 (ESV)

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选