nirholas avatar

Documentation Extractor

nirholas/extract-llms-docs

Pulls llms.txt and install.md files from documentation sites and converts them into structured markdown sections ready for AI consumption. Exposes tools like extract_docs, validate_url, and verify_llms_txt to check for llms.txt support and parse content from platforms like Mintlify, Docusaurus, and GitBook. Useful when you need to feed external documentation into your agent's context or build RAG pipelines from standardized doc formats. Also includes an AI-powered install.md generator that analyzes GitHub repos or documentation URLs to create LLM-executable installation instructions. Returns content as individual markdown files, JSON, YAML, or ZIP archives.

GitHub stars
29
tools
6
last updated
Jan 20, 2026

Tools

6 tools

Public tool metadata for what this MCP can expose to an agent.

extract_docsExtract documentation from a URL with llms.txt support

Extract documentation from a URL with llms.txt support

No parameter schema in public metadata yet.

validate_urlCheck if a URL has llms.txt available

Check if a URL has llms.txt available

No parameter schema in public metadata yet.

verify_llms_txtVerify llms.txt exists and get file info

Verify llms.txt exists and get file info

No parameter schema in public metadata yet.

discover_documentation_urlsFind documentation URLs for a domain

Find documentation URLs for a domain

No parameter schema in public metadata yet.

list_sitesGet directory of known llms.txt-enabled sites

Get directory of known llms.txt-enabled sites

No parameter schema in public metadata yet.

search_sitesSearch the site directory by category or keyword

Search the site directory by category or keyword

No parameter schema in public metadata yet.

Sponsors

Readme

llm.energy

llm.energy - Extract Documentation for AI Agents

Extract llms.txt documentation and install.md instructions from any website for AI agents, LLMs, and automation workflows.

llm.energy

Website Documentation npm version


View the full README on GitHub

Details

Repository
github.com/nirholas/extract-llms-docs
Category
Search & Web Crawling
Registry
MCP registry, active

More from nirholas

Related Search & Web Crawling MCP servers

View all
1dorukardahan avatarDomain Search Mcpdorukardahan/domain-search-mcpNaming engine with availability intelligence: score names, check domains, socials and registries.28stars
2arjunkmrm avatarArjunkmrm Perplexity Searcharjunkmrm/perplexity-searchEnable AI assistants to perform web searches using Perplexity's Sonar Pro.10stars
3tonysimonovsky avatarClaude Code Conversation Search Mcptonysimonovsky/claude-code-conversation-search-mcpSearch Claude Code conversation history with natural language queries across all projects5stars
4efoltyn avatarMarket Searchefoltyn/market-searchKalshi and Polymarket odds, stocks, options, macro, SEC filings and central banks. Runs locally.4stars
5mastadoonprime avatarSylex Searchmastadoonprime/sylex-searchUniversal search engine for AI agents. Discover products, services, and businesses via MCP.3stars
6lulzasaur9192 avatarMarketplace Searchlulzasaur9192/marketplace-search-mcp22 tools: search 15+ marketplaces, verify licenses, childcare costs, FCC, GSA auctions2stars