Polygon x402 AI Data Agent
⚡ x402-cleanweb-agent
Verwandle jede unübersichtliche Webseite, jedes YouTube-Video oder PDF-Paper in sauberes, LLM-bereites Markdown auf Polygon.
Null Anmeldung. Null Abonnements. Echte Machine-to-Machine-HTTP-402-Mikrozahlungen für autonome KI-Agenten.
💡 Warum x402-cleanweb-agent?
Traditionelle Web-Scraping- und Datenextraktions-APIs erzwingen teure $49/Monat-Abonnements und komplexe API-Key-Verwaltung.
x402-cleanweb-agent löst das für autonome KI-Agenten, Scraper und Entwickler:
❌ Keine Monatsabonnements: Bezahle nur für das, was du abfragst ($0.005 ~ $0.05 pro Aufruf in USDC).
❌ Keine Anmeldungen oder API-Keys: Natives HTTP-402-Payment-Required-Machine-to-Machine-Protokoll.
🤖 Bereit für KI-Agenten ohne menschliches Zutun: KI-Agenten mit einer Krypto-Wallet können rund um die Uhr autonom Daten kaufen.
⚡ Unter-Sekunden-Geschwindigkeit: Entfernt Werbung, Tracking-Skripte und Ballast und liefert reines, strukturiertes Markdown.
🪙 Extrem niedrige Gasgebühren: Unterstützt durch Polygon PoS (< $0.005 Netzwerk-Gas).
📊 Token-Spar-Engine: Berechnet die Reduzierung von rohen vs. bereinigten Token (durchschnittlich 60~85 % Ersparnis) sowie geschätzte LLM-Prompt-Kostenersparnis ($).
Related MCP server: ToolSnap MCP
🚀 Live-Demo & Service-Endpunkte
🌐 Web3-DApp-UI: https://x402-cleanweb-agent.onrender.com
📚 Swagger-API-Dokumentation: https://x402-cleanweb-agent.onrender.com/docs
📂 GitHub-Repo: https://github.com/nohosa001-pixel/x402-cleanweb-agent
Dienst | Endpunkt | Preis | Ausgabe & Beschreibung |
🌐 Clean Web |
| 0.01 USDC | Werbungs-/Rausch-Entfernung + KI-bereites Markdown + Token-Spar-Analyse |
🎬 YouTube-Transkript |
| 0.02 USDC | Vollständige Video-Transkripte mit Zeitstempeln in Markdown formatiert |
📑 PDF-Paper & Bericht |
| 0.05 USDC | arXiv-Papers & Gewinnberichte in strukturiertes Markdown umgewandelt |
📝 Reiner Klartext |
| 0.005 USDC | Extrem leichtgewichtige Rohtext-Extraktion für schnelle Vektor-Indizierung |
🤖 Integration autonomer KI-Agenten ohne menschliches Zutun (Python-SDK)
KI-Agenten mit einer Polygon-Wallet (Privater Schlüssel) können Zahlung und Datenextraktion mit null menschlichem Eingriff autonom abwickeln:
from autonomous_agent_client import AutonomousX402Agent
# 1. Initialize Autonomous Agent with Polygon Wallet
agent = AutonomousX402Agent(private_key="0xYOUR_AGENT_PRIVATE_KEY")
# 2. Autonomous Clean Web Extraction (0.01 USDC)
result = agent.clean_web("https://example.com/article")
print("AI-Ready Markdown:\n", result["markdown_content"])
print("Token Savings:", result["token_analytics"]["token_savings_percentage"])
# 3. Autonomous YouTube Transcript Extraction (0.02 USDC)
yt_result = agent.clean_youtube("https://www.youtube.com/watch?v=dQw4w9WgXcQ")
print("YouTube Transcripts:\n", yt_result["markdown_transcript"])
# 4. Autonomous PDF Paper Extraction (0.05 USDC)
pdf_result = agent.clean_pdf("https://arxiv.org/pdf/2301.00001.pdf")
print("PDF Paper Markdown:\n", pdf_result["markdown_content"])🛠️ So funktioniert es (M2M-Architektur)
sequenceDiagram
autonumber
actor Agent as Autonomous AI Agent
participant Server as x402 Gateway (FastAPI)
participant Polygon as Polygon Mainnet (Bor RPC)
participant Scraper as AI Data Cleaning Engine
Agent->>Server: GET /api/v1/clean-web?url=https://example.com
Note over Server: Check X-Payment-Tx header
Server-->>Agent: 402 Payment Required (Chain ID: 137, Recipient, Amount)
Agent->>Polygon: Send USDC Transfer (e.g. 0.01 USDC)
Polygon-->>Agent: Return Tx Hash (0xabc...123)
Agent->>Server: GET /api/v1/clean-web?url=... with Header [X-Payment-Tx: 0xabc...123]
Server->>Polygon: Verify Receipt, Event Logs, Recipient & Nonce
Polygon-->>Server: Tx Confirmed (Status: 1)
Server->>Scraper: Sanitize and Structure to Clean Markdown
Scraper-->>Server: Return Clean Markdown + Token Analytics
Server-->>Agent: 200 OK (Clean Markdown & Analytics JSON)⚡ Direkter cURL-Schnellstart
# Step 1: Query without payment to inspect 402 payment requirements
curl -i -X GET "https://x402-cleanweb-agent.onrender.com/api/v1/clean-web?url=https://example.com"
# Step 2: After sending USDC on Polygon, query with transaction hash
curl -X GET "https://x402-cleanweb-agent.onrender.com/api/v1/clean-web?url=https://example.com" \
-H "X-Payment-Tx: 0x<YOUR_POLYGON_TX_HASH>"Beispielantwort
{
"status": "success",
"service": "clean-web",
"source_url": "https://example.com",
"title": "Example Domain",
"markdown_content": "# Example Domain\n\nThis domain is for use in illustrative examples...",
"token_analytics": {
"raw_html_estimated_tokens": 1250,
"clean_markdown_estimated_tokens": 280,
"tokens_saved": 970,
"token_savings_percentage": "77.6%",
"estimated_llm_cost_saved_usd": "$0.0029"
},
"processing_time_seconds": 0.38
}🔌 Model Context Protocol (MCP)-Einrichtung
Option 1: 1-Klick-Autoinstaller (Empfohlen)
Konfiguriert Claude Desktop & Cursor automatisch, ohne JSON-Dateien zu bearbeiten:
# Windows
install_mcp.bat
# macOS / Linux
python install_mcp.pyOption 2: Ausführung über uvx (Keine Installation erforderlich)
Direkt zu deiner claude_desktop_config.json oder Cursor hinzufügen:
{
"mcpServers": {
"polygon-x402-cleanweb": {
"command": "uvx",
"args": ["--from", "git+https://github.com/nohosa001-pixel/x402-cleanweb-agent", "x402-agent"]
}
}
}Option 3: Manuelle lokale Konfiguration
{
"mcpServers": {
"polygon-x402-cleanweb": {
"command": "python",
"args": ["-u", "/absolute/path/to/x402-micro-agent/mcp_server.py"],
"env": {
"PYTHONUNBUFFERED": "1",
"POLYGON_RPC_URL": "https://polygon-bor-rpc.publicnode.com",
"SERVER_WALLET_ADDRESS": "0x255F9991233f86B29dB847c8d5b8CB9915e80dCf",
"USDC_CONTRACT_ADDRESS": "0x3c499c542cEF5E3811e1192ce70d8cC03d5c3359"
}
}
}
}Verfügbare MCP-Tools
get_payment_info(): Ruft Preismodelle und Empfängeradresse ab.fetch_clean_markdown(url, payment_tx_hash): Clean-Web-Scraper (0.01 USDC).fetch_youtube_transcript(url, language, payment_tx_hash): YouTube-Transkript-Extraktor (0.02 USDC).fetch_pdf_markdown(url, payment_tx_hash): PDF-Forschungspaper-Konverter (0.05 USDC).fetch_plain_text(url, payment_tx_hash): Leichtgewichtiger Text-Scraper (0.005 USDC).
🛠️ Lokale Entwicklung & Ausführung
# 1. Clone repository
git clone https://github.com/nohosa001-pixel/x402-cleanweb-agent.git
cd x402-cleanweb-agent
# 2. Setup virtual environment
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# 3. Install dependencies
pip install -r requirements.txt
# 4. Start local server
python main.py
# Server running at: http://localhost:8000📜 On-Chain-Vertrag & Netzdaten
Netzwerk: Polygon Mainnet (Chain-ID:
137)Token-Vertrag (USDC):
0x3c499c542cEF5E3811e1192ce70d8cC03d5c3359Empfänger-Treasury:
0x255F9991233f86B29dB847c8d5b8CB9915e80dCfStandard: HTTP 402 Payment Required
🤝 Beiträge & Lizenz
Beiträge und Vorschläge sind willkommen!
Erstelle gerne ein Issue oder einen Pull-Request auf GitHub: https://github.com/nohosa001-pixel/x402-cleanweb-agent/issues
Verteilt unter der MIT-Lizenz.
Maintenance
Related MCP Servers
- AlicenseAqualityBmaintenancePay-per-use clean web reader for AI agents. URL in, markdown plus metadata out, in milliseconds. Settled per-call in USDC over x402 — no signup, no API keys.21852MIT
- AlicenseAqualityAmaintenanceContext-efficient MCP server for AI agents. fetch_extract reduces token usage by a median 98.1% (53,820 → 2,001 tokens) vs raw HTML — saves ~$0.156/call at Sonnet pricing. Pay $0.02 USDC on Base via x402. First call free per wallet. 10 always-free utility tools included.331MIT
- AlicenseNot gradedqualityBmaintenanceMCP server providing 17 keyless, pay-per-use web-data tools with signed-provenance receipts, enabling AI agents to autonomously fetch, extract, and verify web content on Base mainnet.44MIT

nanoparse-mcpofficial
AlicenseAqualityBmaintenanceMCP server that enables AI agents to fetch web content as clean, structured Markdown via NanoParse's hosted API, using x402 micropayments in USDC on Base.1253MIT
Related MCP Connectors
Pay-per-call web scraping for AI agents via x402 on Base USDC. Six tools, no signup.
Web intelligence for AI agents: fetch, render, extract, research. x402 micropayments, no API keys.
Scrape, crawl, map and extract the web. Pay per call in USDC, no account or API key.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/nohosa001-pixel/x402-cleanweb-agent'
If you have feedback or need assistance with the MCP directory API, please join our Discord server