Extract LLMs Docs
Extract documentation for AI agents from any site with llms.txt support. Features MCP server, REST API, batch processing, and multiple export formats.
What is Extract LLMs Docs?
Extract LLMs Docs is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to extract documentation for ai agents from any site with llms.txt support. features mcp server, rest api, batch processing, and multiple export formats.
Extract documentation for AI agents from any site with llms.txt support. Features MCP server, REST API, batch processing, and multiple export formats.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Extract documentation for AI agents from any site with llms.
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx extract-llms-docsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Extract LLMs Docs
Extract LLMs Docs (llm.energy) is an MCP server that lets AI assistants fetch and process developer documentation from any website that publishes an llms.txt file — the emerging standard for AI-readable site indexes. It provides tools to extract docs in clean Markdown, validate whether a site supports llms.txt, discover documentation URLs, and browse a directory of known llms.txt-enabled sites, enabling AI coding agents to pull accurate, up-to-date library documentation on demand rather than relying on training data.
Prerequisites
- Node.js 18+ installed for running npx
- An MCP-compatible client such as Claude Desktop, Cursor, or VS Code
- Internet access to reach target documentation sites
- Optional: ADMIN_KEY environment variable for cache management operations
Install and run via npx
The MCP server is published under @llm-energy/mcp-server and can be run directly with npx without a prior install step.
npx -y @llm-energy/mcp-serverAdd the server to your MCP client config
Add the extract-llms-docs server to your Claude Desktop or Cursor configuration. No API keys are required for basic usage.
{
"mcpServers": {
"extract-llms-docs": {
"command": "npx",
"args": ["-y", "@llm-energy/mcp-server"]
}
}
}Restart your MCP client
Restart Claude Desktop or your MCP client to load the new server. You should see tools like extract_docs, validate_url, and list_sites become available.
Validate a site's llms.txt support
Before extracting docs, use validate_url to check if a target site supports llms.txt. This quickly confirms whether full documentation extraction will work.
Extract documentation from a site
Use the extract_docs tool with a URL to pull clean Markdown documentation from any llms.txt-enabled site. The result is structured content ready for AI consumption.
Extract LLMs Docs Examples
Client configuration
Claude Desktop configuration for the Extract LLMs Docs MCP server.
{
"mcpServers": {
"extract-llms-docs": {
"command": "npx",
"args": ["-y", "@llm-energy/mcp-server"],
"env": {
"ADMIN_KEY": "optional_admin_key_for_cache_management"
}
}
}
}Prompts to try
Example prompts for extracting and searching developer documentation.
- "Check if https://docs.anthropic.com supports llms.txt"
- "Extract the documentation from https://fastapi.tiangolo.com using llms.txt"
- "Discover all documentation URLs available at https://nextjs.org"
- "List known sites that support llms.txt and filter by developer tools"
- "Search the llms.txt site directory for Python libraries"Troubleshooting Extract LLMs Docs
extract_docs returns no content or an error for a site
First use validate_url to confirm the site supports llms.txt. If it does not, the site has not published an llms.txt file and documentation cannot be extracted with this tool.
Rate limit errors when extracting docs from multiple sites
The server enforces rate limits (default: 100 requests per 60-second window). Space out your requests or self-host the server and set RATE_LIMIT_REQUESTS and RATE_LIMIT_WINDOW_MS to higher values.
Stale documentation being returned from cache
The server caches results for CACHE_TTL seconds (default 3600). To flush the cache for a specific site, use the admin API endpoint with your ADMIN_KEY, or wait for the cache to expire.
Frequently Asked Questions about Extract LLMs Docs
What is Extract LLMs Docs?
Extract LLMs Docs is a Model Context Protocol (MCP) server that extract documentation for ai agents from any site with llms.txt support. features mcp server, rest api, batch processing, and multiple export formats. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Extract LLMs Docs?
Follow the installation instructions on the Extract LLMs Docs GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Extract LLMs Docs?
Extract LLMs Docs works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Extract LLMs Docs free to use?
Yes, Extract LLMs Docs is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Extract LLMs Docs Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Extract LLMs Docs? 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 Extract LLMs Docs 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 Extract LLMs Docs?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.