JW.org
A Model Context Protocol (MCP) server that provides controlled, verifiable access to content from jw.org for AI applications and LLM integrations.
What is JW.org?
JW.org is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server that provides controlled, verifiable access to content from jw.org for ai applications and llm integrations.
A Model Context Protocol (MCP) server that provides controlled, verifiable access to content from jw.org for AI applications and LLM integrations.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol (MCP) server that provides controll
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx jw-orgConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use JW.org
The JW.org MCP Server provides controlled, verifiable access to publications, articles, scriptures, and videos from jw.org for AI assistants. It exposes tools for semantic content search, full article retrieval, and scripture lookup with built-in caching and language support — making it straightforward to integrate JW.org content into Claude or any MCP-compatible application.
Prerequisites
- Python 3.10+ with uv installed (https://docs.astral.sh/uv/getting-started/installation/)
- Git to clone the repository
- Claude Desktop installed on macOS or Windows
- Internet access to reach jw.org and wol.jw.org at runtime
Clone the repository and sync dependencies
Clone the jw-org-mcp repository and use uv to install all dependencies. uv creates an isolated virtual environment automatically based on the project's pyproject.toml.
git clone https://github.com/Bjern/jw-org-mcp.git
cd jw-org-mcp
uv sync
# With development dependencies:
uv sync --group devConfigure optional environment variables
All configuration uses the JWORG_MCP_ prefix and has sensible defaults. You only need to set variables if you want to change the default language, cache behavior, or logging. Create a .env file or export the variables in your shell.
# Optional: override defaults
export JWORG_MCP_DEFAULT_LANGUAGE=E
export JWORG_MCP_CACHE_TTL_SECONDS=900
export JWORG_MCP_ENABLE_CACHE=true
export JWORG_MCP_DEFAULT_SEARCH_LIMIT=10
export JWORG_MCP_LOG_LEVEL=INFOTest the server from the command line
Run the server directly with uv to confirm it starts without errors. It will wait for MCP stdio input. Press Ctrl+C to stop after confirming startup succeeds.
uv run jw-org-mcpAdd the server to Claude Desktop
Edit the Claude Desktop configuration file for your operating system. The command uses uv with the --directory flag pointing to your cloned repository. Restart Claude Desktop after saving the configuration.
Verify the tools are accessible in Claude
Ask Claude to search for a scripture or article. The server provides four tools: search_content, get_article, get_scripture, and get_cache_stats. A successful response with real content confirms the server is working.
JW.org Examples
Client configuration
Claude Desktop configuration for macOS. Replace /path/to/jw-org-mcp with the absolute path where you cloned the repository. The Windows path is %APPDATA%\Claude\claude_desktop_config.json.
{
"mcpServers": {
"jw-org": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/jw-org-mcp",
"run",
"jw-org-mcp"
]
}
}
}Prompts to try
Natural language prompts that use the search_content, get_scripture, and get_article tools to retrieve verified content from jw.org.
- "What does the Bible say about love? Search jw.org for articles."
- "Look up John 3:16 using the NWT translation"
- "Search jw.org publications for information about prayer"
- "Find videos on jw.org about family relationships"
- "Get the full article from this wol.jw.org URL: https://wol.jw.org/en/wol/d/r1/lp-e/1985720"
- "Search the Bible for verses mentioning faith, limit to 5 results"Troubleshooting JW.org
search_content returns no results or HTTP errors
The server fetches content from jw.org at runtime. Check your internet connection and verify jw.org is accessible from your machine. If you are behind a corporate proxy, configure Python's HTTP proxy settings via the HTTP_PROXY and HTTPS_PROXY environment variables.
uv command not found when Claude Desktop tries to start the server
Claude Desktop launches the server using the system PATH. Install uv system-wide: `curl -LsSf https://astral.sh/uv/install.sh | sh`. If uv is installed in a user path not on the system PATH, provide the absolute path to the uv binary in the command field instead of just 'uv'.
Language codes return unexpected content or errors
The DEFAULT_LANGUAGE setting uses JW.org language codes, not ISO codes. English is 'E', Spanish is 'S', French is 'F', German is 'X'. Check the jw.org language selector for the correct two-letter code for your language.
Frequently Asked Questions about JW.org
What is JW.org?
JW.org is a Model Context Protocol (MCP) server that model context protocol (mcp) server that provides controlled, verifiable access to content from jw.org for ai applications and llm integrations. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install JW.org?
Follow the installation instructions on the JW.org GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with JW.org?
JW.org works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is JW.org free to use?
Yes, JW.org is open source and available under the GPL-3.0 license. You can use it freely in both personal and commercial projects.
JW.org Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to JW.org? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up JW.org in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use JW.org?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.