llm.energy MCP server
Commit 15. Nov. 2026Extrahiert llms.txt und install.md Dokumentationen von Websites in strukturiertes, agentenfertiges Markdown für AI-Clients.
Auch bekannt als nirholas/extract-llms-docs, extract-llms-docs
- Stars
- 35
- Tools
- 9
- Downloads, 30 Tage
- —
- Neueste Version
- 1.0.0
- Letzter Commit
- 15. Nov. 2026
- Lizenz
- —
Was ist llm.energy MCP?
Extrahiert llms.txt und install.md Dokumentationen von Websites in strukturiertes, agentenfertiges Markdown für AI-Clients. Er stellt 9 Tools bereit, etwa extract_docs, validate_url, verify_llms_txt.
Zusammenfassung generiert aus dem README des Projekts
Über llm.energy MCP server
Der Documentation Extractor ermöglicht es, Website-Dokumentationen in strukturierte Formate für AI Agents umzuwandeln. Er konzentriert sich speziell auf Websites, die die llms.txt und install.md Standards implementieren, und transformiert Rohdaten in agentenfertiges Markdown, JSON, YAML oder ZIP-Archive. Entwickler können dies nutzen, um Coding-Assistenten wie Cursor oder Windsurf mit aktuellem Kontext zu füttern.
Nutzer verbinden den Server via npx mit Clients wie Claude Desktop oder Cursor. Der Server bietet spezialisierte Tools wie extract_docs, validate_url und discover_documentation_urls, um Agents dabei zu helfen, technische Informationen zu navigieren und zu erfassen. Er kann zudem mehrere URLs gleichzeitig durch Batch-Verarbeitung verarbeiten.
Über die reine Extraktion hinaus kann das System neue Dokumentationen generieren. Es verfügt über einen KI-gestützten Generator, der install.md Dateien erstellt, indem er öffentliche GitHub Repositories, bestehende Dokumentations-URLs oder manuelle Eingaben analysiert. Das macht es zu einem vielseitigen Tool, um sowohl externes Wissen zu konsumieren als auch eigene Projekte für KI-gestützte Workflows vorzubereiten.
Was du damit machen kannst
- 1Dokumentation an Coding-Assistenten fütternVersorge AI Tools wie Cursor oder Windsurf mit aktuellem technischem Kontext.
- 2Installationsanweisungen aus GitHub generierenErstelle ausführbare Installationsdateien durch die Analyse der Struktur eines öffentlichen Repositories.
- 3Dokumentations-Pipelines für RAG automatisierenBaue automatisierte Workflows, die Dokumentationen für Retrieval-Augmented Generation Systeme aggregieren und strukturieren.
- 4Dokumentations-Standards verifizierenPrüfe, ob eine bestimmte Website den llms.txt Standard unterstützt, bevor du mit der Extraktion beginnst.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
llm.energy MCP tools 9
Erkannt aus dem READMEextract_docsvalidate_urlverify_llms_txtdiscover_documentation_urlslist_sitessearch_sitesfetch_llms_txtfetch_llms_full_txtextract_documentation
| extract_docs | — | |
| validate_url | — | |
| verify_llms_txt | — | |
| discover_documentation_urls | — | |
| list_sites | — | |
| search_sites | — | |
| fetch_llms_txt | — | |
| fetch_llms_full_txt | — | |
| extract_documentation | — |
Automatisierte Checks
Geluften am 14. Nov. 2026Vollständiger Bericht →Noch nicht verifiziert. Ein Server benötigt einen Score von 80, keine kritischen Befunde und genug Daten für unsere Prüfung. Wie die Checks funktionieren · Was du für mehr Punkte verbessern kannst
- Source Repository verknüpft und erreichbarnirholas/extract-llms-docs is public and reachablegithub.com/nirholas/extract-llms-docs ↗Bestanden
- Paket nennt dieses Repository als QuelleNicht geprüft
- Build-Provenienz (Sigstore-Attestierung)Nicht geprüft
- Open Source Lizenz (OSI)No licenseBefund
- Commit oder Release im letzten JahrLast commit or release 2026-11-13github.com/nirholas/extract-llms-docs ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNicht geprüft
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenNicht geprüft
- Keine versteckten Anweisungen an das Modell9 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNo tool named like delete, drop or execBestanden
- Remote-Endpoint beantwortet den MCP-HandshakeNicht geprüft
README
Auf GitHub ansehenllm.energy
📖 Overview
llm.energy is a web application and MCP server that fetches, parses, and organizes documentation from websites implementing the llms.txt and install.md standards. It transforms raw documentation into structured, agent-ready formats optimized for large language models, AI assistants, and developer tooling.
| Standard | Description | Learn More |
|---|---|---|
| llms.txt | Machine-readable documentation for AI systems | llmstxt.org |
| install.md | LLM-executable installation instructions | installmd.org |
✨ Key Features
| Feature | Description |
|---|---|
| 🔍 Smart Detection | Automatically finds llms.txt, llms-full.txt, and install.md |
| 📄 Organized Output | Splits content into individual markdown files by section |
| 🤖 Agent-Ready | Includes AGENT-GUIDE.md optimized for AI assistants |
| 📦 Multiple Formats | Export as Markdown, JSON, YAML, or ZIP archive |
| 🔌 MCP Server | Integrate with Claude Desktop, Cursor, and more |
| ⚡ Batch Processing | Process multiple URLs simultaneously |
| 📚 Site Directory | Browse 19+ curated llms.txt-enabled websites |
| ✏️ llms.txt Generator | Create your own llms.txt files with a guided wizard |
| 🚀 install.md Generator | AI-powered: generate from GitHub repos, docs URLs, or manually |
🎯 Use Cases
─────────────────────────────────────────────────────────────────
📝 Feed docs to AI coding assistants (Cursor, Windsurf)
🤖 Build context-aware AI agents with up-to-date docs
🔄 Create documentation pipelines for RAG systems
📦 Aggregate docs from multiple sources automatically
✏️ Generate llms.txt/install.md for your own projects
🚀 Auto-generate install.md from any GitHub repo
─────────────────────────────────────────────────────────────────
🚀 install.md Generator
Generate LLM-executable installation instructions from any source:
| Mode | Description | Use Case |
|---|---|---|
| From GitHub | Analyze any public GitHub repo and generate install.md | Perfect for creating install.md for existing projects |
| From URL | Extract from any documentation page | Convert existing docs to install.md format |
| Manual | Build from scratch with guided wizard | Full control over every detail |
How It Works
- GitHub Mode: Analyzes README, package.json/pyproject.toml/Cargo.toml, GitHub Actions, and releases
- URL Mode: Scrapes documentation pages, detects platforms (Mintlify, Docusaurus, GitBook, etc.)
- AI Synthesis: Uses Claude to generate a properly formatted install.md
Quick Example
# Generate install.md for any GitHub project
curl -X POST https://llm.energy/api/generate-install \
-H "Content-Type: application/json" \
-d '{"url": "https://github.com/anthropics/anthropic-sdk-python", "type": "github"}'
Visit llm.energy/install-generator to use the web interface.
📚 Documentation
Full documentation is available at llm.energy/docs
🚀 Installation
Web Application
Visit llm.energy to use the hosted version.
Local Development
# Clone the repository
git clone https://github.com/nirholas/extract-llms-docs.git
cd extract-llms-docs
# Install dependencies
pnpm install
# Start development server
pnpm dev
🌐 The application runs on http://localhost:3001
MCP Server
Add to your MCP client configuration (Claude Desktop, Cursor, etc.):
{
"mcpServers": {
"llm-energy": {
"command": "npx",
"args": ["-y", "@llm-energy/mcp-server"]
}
}
}
See MCP Server Documentation for detailed setup.
🔌 API Reference
curl -X POST https://llm.energy/api/extract \
-H "Content-Type: application/json" \
-d '{"url": "docs.anthropic.com"}'
Response includes parsed sections, metadata, and download URLs.
curl -X POST https://llm.energy/api/validate \
-H "Content-Type: application/json" \
-d '{"url": "docs.example.com"}'
curl -X POST https://llm.energy/api/batch \
-H "Content-Type: application/json" \
-d '{"urls": ["docs.anthropic.com", "docs.stripe.com"]}'
# Formats: markdown, json, yaml, zip
curl "https://llm.energy/api/download?url=docs.anthropic.com&format=zip"
# Generate from a GitHub repository
curl -X POST https://llm.energy/api/generate-install \
-H "Content-Type: application/json" \
-d '{"url": "https://github.com/anthropics/anthropic-sdk-python", "type": "github"}'
# Generate from a documentation URL
curl -X POST https://llm.energy/api/generate-install \
-H "Content-Type: application/json" \
-d '{"url": "https://docs.anthropic.com/en/docs/quickstart", "type": "docs"}'
# Analyze only (preview mode)
curl "https://llm.energy/api/generate-install?url=https://github.com/anthropics/anthropic-sdk-python&type=github"
🤖 MCP Server Tools
The MCP server exposes the following tools for AI agents:
| Tool | Description |
|---|---|
extract_docs |
Extract documentation from a URL with llms.txt support |
validate_url |
Check if a URL has llms.txt available |
verify_llms_txt |
Verify llms.txt exists and get file info |
discover_documentation_urls |
Find documentation URLs for a domain |
list_sites |
Get directory of known llms.txt-enabled sites |
search_sites |
Search the site directory by category or keyword |
🏗️ Architecture
┌──────────────────────────────────────────────────────────────────┐
│ llm.energy │
├──────────────────────────────────────────────────────────────────┤
│ │
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
│ │ Web App │ │ REST API │ │ MCP Server │ │
│ │ (Next.js) │ │ /api/* │ │ (stdio) │ │
│ └──────┬──────┘ └──────┬──────┘ └──────┬──────┘ │
│ │ │ │ │
│ └────────────────┼────────────────┘ │
│ │ │
│ ┌──────▼──────┐ │
│ │ Core │ │
│ │ - Parser │ │
│ │ - Extractor│ │
│ │ - Cache │ │
│ └──────┬──────┘ │
│ │ │
│ ┌────────────────┼────────────────┐ │
│ ▼ ▼ ▼ │
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
│ │ llms.txt │ │ install.md │ │ Sitemap │ │
│ └─────────────┘ └─────────────┘ └─────────────┘ │
│ │
└──────────────────────────────────────────────────────────────────┘
extract-llms-docs/
├── src/
│ ├── app/ # Next.js pages and API routes
│ │ ├── api/ # REST API endpoints
│ │ │ ├── extract/ # Documentation extraction API
│ │ │ ├── generate-install/ # AI-powered install.md generation
│ │ │ └── ... # Other API endpoints
│ │ ├── extract/ # Extraction interface
│ │ ├── batch/ # Batch processing page
│ │ ├── directory/ # Site directory browser
│ │ ├── generator/ # llms.txt generator wizard
│ │ └── install-generator/ # install.md generator with tabs
│ ├── components/ # React UI components
│ │ └── install-generator/ # GitHubTab, UrlTab, Preview
│ ├── lib/ # Core utilities
│ │ ├── github-analyzer.ts # GitHub repo analysis
│ │ ├── docs-analyzer.ts # Documentation URL scraping
│ │ └── ... # Parser, extractor, cache
│ ├── hooks/ # React hooks
│ └── types/ # TypeScript definitions
├── packages/core/ # Shared parser and types
├── mcp-server/ # MCP server package
└── docs-site/ # MkDocs documentation source
🛠️ Technology Stack
⚙️ Configuration
All environment variables are optional — the app runs without them. Copy .env.example to
.env.local and fill in only what you need:
cp .env.example .env.local
| Variable | Used by | Default | Purpose |
|---|---|---|---|
ADMIN_KEY |
/api/cache |
unset | Value the x-admin-key header must match for cache management. Both GET and POST return 500 when it is unset. Production reads it from Secret Manager (llm-energy-admin-key). |
ANTHROPIC_API_KEY |
/api/generate-install |
unset | Enables Claude-backed generation of install.md. The endpoint returns a configuration error without it. |
VERIFY_TIMEOUT_MS |
/api/sites/verify |
10000 |
Per-site fetch timeout, in milliseconds. |
VERIFY_CACHE_TTL_MS |
/api/sites/verify |
300000 |
How long verification results are cached, in milliseconds. |
HEALTH_TIMEOUT_MS |
/api/sites/health |
8000 |
Timeout for site health probes, in milliseconds. |
🚀 Deployment
| Hostname | Serves | Hosted on |
|---|---|---|
llm.energy, www.llm.energy |
The Next.js app and its /api/* routes |
Cloud Run service llm-energy, fronted by the Cloudflare Worker llm-energy-proxy |
| docs.llm.energy | MkDocs site built from docs-site/ |
Cloudflare Pages project llm-energy |
Redeploy commands, DNS layout and rollback: docs/deploy-cloudflare.md.
💻 Development
pnpm dev # 🚀 Start development server
pnpm build # 📦 Production build
pnpm start # ▶️ Start production server
pnpm test # 🧪 Run tests (163 tests)
pnpm test:coverage # 📊 Tests with coverage report
pnpm typecheck # ✅ TypeScript validation
pnpm lint # 🔍 ESLint check
🔗 Related Projects
| Project | Description |
|---|---|
| llms.txt Standard | Machine-readable documentation format |
| install.md Standard | LLM-executable installation format |
| Model Context Protocol | Protocol for AI tool integration |
| MCP Servers Directory | Community MCP servers |
🌐 Sites with llms.txt Support
Browse 19+ curated websites with verified llms.txt support at llm.energy/directory
Featured sites include:
- 🤖 Anthropic Documentation
- ⚡ Vercel Documentation
- 💳 Stripe API Reference
- 🗄️ Supabase Docs
- 📘 Mintlify Documentation
- ...and more!
🤝 Contributing
Contributions are welcome! Please follow these steps:
- 🍴 Fork the repository
- 🌿 Create a feature branch (
git checkout -b feature/amazing-feature) - 💾 Commit your changes (
git commit -m 'Add amazing feature') - 📤 Push to the branch (
git push origin feature/amazing-feature) - 🔀 Open a Pull Request
Adding a site to the directory? Edit src/data/sites.ts and submit a PR.
📄 License
Proprietary — Copyright 2026 nirholas, all rights reserved. See LICENSE for details.
🔗 Links
👤 Author
Built by nich
Author
Built by nich - https://x.com/nichxbt
Comprehensive keyword list for ERC-8004 Trustless Agents ecosystem
Core Protocol Keywords
ERC-8004, ERC8004, EIP-8004, EIP8004, Trustless Agents, trustless agent, trustless AI, trustless AI agents, agent protocol, agent standard, Ethereum agent standard, blockchain agent protocol, on-chain agents, onchain agents, on-chain AI, onchain AI, decentralized agents, decentralized AI agents, autonomous agents, autonomous AI agents, AI agent protocol, AI agent standard, agent discovery, agent trust, agent reputation, agent validation, agent identity, agent registry, identity registry, reputation registry, validation registry, agent NFT, ERC-721 agent, agent tokenId, agentId, agentURI, agentWallet, agent registration, agent registration file, agent-registration.json, agent card, agent metadata, agent endpoints, agent discovery protocol, agent trust protocol, open agent protocol, open agent standard, permissionless agents, permissionless AI, censorship-resistant agents, portable agent identity, portable AI identity, verifiable agents, verifiable AI agents, accountable agents, accountable AI, agent accountability
Blockchain & Web3 Keywords
Ethereum, Ethereum mainnet, ETH, EVM, Ethereum Virtual Machine, smart contracts, Solidity, blockchain, decentralized, permissionless, trustless, on-chain, onchain, L2, Layer 2, Base, Optimism, Polygon, Linea, Arbitrum, Scroll, Monad, Gnosis, Celo, Sepolia, testnet, mainnet, singleton contracts, singleton deployment, ERC-721, NFT, non-fungible token, tokenURI, URIStorage, EIP-712, ERC-1271, wallet signature, EOA, smart contract wallet, gas fees, gas sponsorship, EIP-7702, subgraph, The Graph, indexer, blockchain indexing, IPFS, decentralized storage, content-addressed, immutable data, public registry, public good, credibly neutral, credibly neutral infrastructure, open protocol, open standard, Web3, crypto, cryptocurrency, DeFi, decentralized finance
AI & Agent Technology Keywords
AI agents, artificial intelligence agents, autonomous AI, AI autonomy, LLM agents, large language model agents, machine learning agents, ML agents, AI assistant, AI chatbot, intelligent agents, software agents, digital agents, virtual agents, AI automation, automated agents, agent-to-agent, A2A, A2A protocol, Google A2A, Agent2Agent, MCP, Model Context Protocol, agent communication, agent interoperability, agent orchestration, agent collaboration, multi-agent, multi-agent systems, agent capabilities, agent skills, agent tools, agent prompts, agent resources, agent completions, AgentCard, agent card, agent endpoint, agent service, AI service, AI API, agent API, AI infrastructure, agent infrastructure, agentic, agentic web, agentic economy, agentic commerce, agent economy, agent marketplace, AI marketplace, agent platform, AI platform
Trust & Reputation Keywords
trust, trustless, reputation, reputation system, reputation protocol, reputation registry, feedback, client feedback, user feedback, on-chain feedback, on-chain reputation, verifiable reputation, portable reputation, reputation aggregation, reputation scoring, reputation algorithm, trust signals, trust model, trust verification, trust layer, recursive reputation, reviewer reputation, spam prevention, Sybil attack, Sybil resistance, anti-spam, feedback filtering, trusted reviewers, rating, rating system, quality rating, starred rating, uptime rating, success rate, response time, performance history, track record, audit trail, immutable feedback, permanent feedback, feedback response, appendResponse, giveFeedback, revokeFeedback, feedback tags, feedback value, valueDecimals, feedbackURI, feedbackHash, clientAddress, reviewer address
Validation & Verification Keywords
validation, validation registry, validator, validator contract, cryptographic validation, cryptographic proof, cryptographic attestation, zero-knowledge, ZK, zkML, zero-knowledge machine learning, ZK proofs, trusted execution environment, TEE, TEE attestation, TEE oracle, stake-secured, staking validators, crypto-economic security, inference re-execution, output validation, work verification, third-party validation, independent validation, validation request, validation response, validationRequest, validationResponse, requestHash, responseHash, verifiable computation, verified agents, verified behavior, behavioral validation, agent verification
Payment & Commerce Keywords
x402, x402 protocol, x402 payments, programmable payments, micropayments, HTTP payments, pay-per-request, pay-per-task, agent payments, AI payments, agent monetization, AI monetization, agent commerce, AI commerce, agentic commerce, agent economy, AI economy, agent marketplace, service marketplace, agent-to-agent payments, A2A payments, stablecoin payments, USDC, crypto payments, on-chain payments, payment settlement, programmable settlement, proof of payment, proofOfPayment, payment receipt, payment verification, Coinbase, Coinbase x402, agent pricing, API pricing, service pricing, subscription, API keys, revenue, trading yield, cumulative revenues, agent wallet, payment address, toAddress, fromAddress, txHash
Discovery & Registry Keywords
agent discovery, service discovery, agent registry, identity registry, agent registration, register agent, mint agent, agent NFT, agent tokenId, agent browsing, agent explorer, agent scanner, 8004scan, 8004scan.io, agentscan, agentscan.info, 8004agents, 8004agents.ai, agent leaderboard, agent ranking, top agents, agent listing, agent directory, agent catalog, agent index, browse agents, search agents, find agents, discover agents, agent visibility, agent discoverability, no-code registration, agent creation, create agent, my agents, agent owner, agent operator, agent transfer, transferable agent, portable agent
Endpoints & Integration Keywords
endpoint, agent endpoint, service endpoint, API endpoint, MCP endpoint, A2A endpoint, web endpoint, HTTPS endpoint, HTTP endpoint, DID, decentralized identifier, ENS, Ethereum Name Service, ENS name, agent.eth, vitalik.eth, email endpoint, OASF, Open Agent Specification Format, endpoint verification, domain verification, endpoint ownership, .well-known, well-known, agent-registration.json, endpoint domain, endpoint URL, endpoint URI, base64 data URI, on-chain metadata, off-chain metadata, metadata storage, JSON metadata, agent JSON, registration JSON
SDK & Developer Tools Keywords
SDK, Agent0 SDK, Agent0, ChaosChain SDK, ChaosChain, Lucid Agents, Daydreams AI, create-8004-agent, npm, TypeScript SDK, Python SDK, JavaScript, Solidity, smart contract, ABI, contract ABI, deployed contracts, contract addresses, Hardhat, development tools, developer tools, dev tools, API, REST API, GraphQL, subgraph, The Graph, indexer, blockchain explorer, Etherscan, contract verification, open source, MIT license, CC0, public domain, GitHub, repository, code repository, documentation, docs, best practices, reference implementation
Ecosystem & Community Keywords
ecosystem, community, builder, builders, developer, developers, contributor, contributors, partner, partners, collaborator, collaborators, co-author, co-authors, MetaMask, Ethereum Foundation, Google, Coinbase, Consensys, AltLayer, Virtuals Protocol, Olas, EigenLayer, Phala, ElizaOS, Flashbots, Polygon, Base, Optimism, Arbitrum, Scroll, Linea, Monad, Gnosis, Celo, Near Protocol, Filecoin, Worldcoin, ThirdWeb, ENS, Collab.land, DappRadar, Giza Tech, Theoriq, OpenServ, Questflow, Semantic, Semiotic, Cambrian, Nevermined, Oasis, Towns Protocol, Warden Protocol, Terminal3, Pinata Cloud, Silence Labs, Rena Labs, Index Network, Trusta Network, Turf Network
Key People & Organizations Keywords
Marco De Rossi, MetaMask AI Lead, Davide Crapis, Ethereum Foundation AI, Head of AI, Jordan Ellis, Google engineer, Erik Reppel, Coinbase engineering, Head of Engineering, Sumeet Chougule, ChaosChain founder, YQ, AltLayer co-founder, Wee Kee, Virtuals contributor, Cyfrin audit, Nethermind audit, Ethereum Foundation Security Team, security audit, audited contracts
llm.energy MCP Fragen
Welche Tools bietet llm.energy MCP?
Er stellt 9 Tools bereit, darunter extract_docs, validate_url, verify_llms_txt, discover_documentation_urls, list_sites.
Was extrahiert llm.energy von einer Website?
Es ruft llms.txt, llms-full.txt und install.md Dateien von Seiten ab, die diese Standards implementieren, und organisiert sie in strukturiertem Markdown.
Welche MCP Tools bietet der llm.energy Server?
Der Server stellt Tools wie extract_docs, validate_url, verify_llms_txt, discover_documentation_urls, list_sites und search_sites bereit.
Wie füge ich den llm.energy MCP server meinem Client hinzu?
Füge in deiner Client-Konfiguration einen mcpServers Eintrag namens llm-energy hinzu, der npx -y @llm-energy/mcp-server ausführt.
Kann llm.energy mehrere URLs gleichzeitig verarbeiten?
Ja, die Batch-API akzeptiert eine Liste von URLs und verarbeitet sie zusammen. Die Exportformate umfassen Markdown, JSON, YAML und ZIP.
Kann es eine install.md für mein Projekt generieren?
Ja, der install.md Generator kann ein öffentliches GitHub Repo analysieren, eine Docs-URL scrapen oder eine Datei manuell erstellen.