This server lets Claude pay per scrape using USDC on Base, no signup required. You get six tools: scrape any page to markdown or JSON, extract structured data with Llama 4 Scout, screenshot with viewport control, pull metadata and Open Graph tags, create stateful browser sessions with cookies, and run multi-step workflows that click, type, and extract atomically. It implements x402 payment protocol over Streamable HTTP, so your first call returns 402 with payment requirements, your wallet signs the transfer, and the data flows back. Runs on Cloudflare Workers with Puppeteer for rendering. Costs $0.001 per call during validation, ramping to $0.002–$0.008 after launch window. Useful when you need real browser rendering or AI-powered extraction without managing API keys or subscriptions.
Public tool metadata for what this MCP can expose to an agent.
scrape_webpageScrape any webpage and return content as markdown, html, text, or json. Pay-per-call web scraping for AI agents.5 paramsScrape any webpage and return content as markdown, html, text, or json. Pay-per-call web scraping for AI agents.
urlstringformatstringmarkdown · html · text · jsonwait_msnumberviewportstringdesktop · mobile · tabletwait_forstringextract_structured_dataAI-powered structured data extraction from any webpage using natural language. Returns JSON matching your prompt or schema.5 paramsAI-powered structured data extraction from any webpage using natural language. Returns JSON matching your prompt or schema.
urlstringpromptstringschemaobjectwait_msnumberwait_forstringscreenshot_webpageCapture a PNG screenshot of any webpage. Supports desktop, mobile, and tablet viewports, plus full-page mode.5 paramsCapture a PNG screenshot of any webpage. Supports desktop, mobile, and tablet viewports, plus full-page mode.
urlstringwait_msnumberviewportstringdesktop · mobile · tabletwait_forstringfull_pagebooleanextract_metadataExtract page metadata: title, description, Open Graph, Twitter cards, JSON-LD, canonical URL, and all meta tags.1 paramsExtract page metadata: title, description, Open Graph, Twitter cards, JSON-LD, canonical URL, and all meta tags.
urlstringcreate_browser_sessionCreate a stateful browser session that persists cookies and localStorage across multiple scrape/workflow calls.1 paramsCreate a stateful browser session that persists cookies and localStorage across multiple scrape/workflow calls.
ttl_secondsnumberrun_workflowExecute a multi-step browser workflow atomically: navigate, click, type, wait, scroll, screenshot, extract, evaluate. Up to 20 steps.4 paramsExecute a multi-step browser workflow atomically: navigate, click, type, wait, scroll, screenshot, extract, evaluate. Up to 20 steps.
stepsarrayviewportstringdesktop · mobile · tabletsession_idstringpersist_sessionbooleanPay-per-call web scraping for AI agents — no signup, no API keys, just USDC.
Live: agent-scrape.healingsunhaven.workers.dev
AI agents discover AgentScrape, pay per call in USDC on Base, and get clean structured data back — no accounts, no API keys, no human in the loop.
Two protocols, one service:
Traditional scraping APIs assume a human:
AI agents can't do any of that. They have wallets. They have stablecoins. They need infrastructure built for them.
AgentScrape speaks two open standards:
No signup. No API keys. No subscription. Just USDC.
All tools cost $0.001 USDC during the mainnet validation window. Pricing ramps after stability is proven (see Pricing).
| Tool | Description |
|---|---|
scrape_webpage | Scrape any URL to markdown, HTML, text, or JSON |
extract_structured_data | AI-powered structured extraction with natural-language prompts and JSON schemas (Groq + Llama 4 Scout) |
screenshot_webpage | PNG screenshot with viewport control (desktop/mobile/tablet, optional full-page) |
extract_metadata | Title, description, Open Graph, Twitter cards, JSON-LD, canonical URL |
create_browser_session | Stateful browser session with cookie + localStorage persistence |
run_workflow | Multi-step atomic execution: navigate, click, type, wait, scroll, screenshot, extract, evaluate |
# Free service discovery (no payment)
curl https://agent-scrape.healingsunhaven.workers.dev/
# Paid call — without payment, returns 402 with payment requirements
curl -X POST https://agent-scrape.healingsunhaven.workers.dev/scrape \
-H "Content-Type: application/json" \
-d '{"url": "https://example.com", "format": "markdown"}'
# Free tier — first 10 calls per wallet, send your wallet in the X-402-Payer header
curl -X POST https://agent-scrape.healingsunhaven.workers.dev/scrape \
-H "Content-Type: application/json" \
-H "X-402-Payer: 0xYourBaseWalletAddress" \
-d '{"url": "https://example.com", "format": "markdown"}'
Add to any MCP-compatible client via Streamable HTTP:
{
"mcpServers": {
"agent-scrape": {
"url": "https://agent-scrape.healingsunhaven.workers.dev/mcp",
"transport": "streamable-http"
}
}
}
The x402 payment metadata is broadcast inside the MCP tools/list response. Your client handles the payment handshake automatically when configured with an x402-compatible wallet.
For machine-driven discovery, four standard endpoints are exposed (free, no auth):
| Endpoint | Purpose |
|---|---|
/ | Service profile JSON (tools, prices, network, payTo) |
/.well-known/x402 (and .json alias) | x402 manifest — payTo, network, facilitator, all paid routes |
/openapi.json | OpenAPI 3.1 spec for traditional tooling |
/llms.txt | Agent-friendly plaintext description |
The 402 response itself carries the canonical payment requirements in the base64-encoded Payment-Required header, and the body includes a human-readable error with discovery links.
┌──────────────────────────────────┐
│ Cloudflare Workers │
│ (global edge, 330+ POPs) │
│ │
AI Agent ───────┼─▶ GET / (free)│
(HTTP) ├─▶ GET /.well-known/x402 (free)│
├─▶ GET /openapi.json (free)│
├─▶ GET /llms.txt (free)│
├─▶ POST /scrape ($0.001) │
├─▶ POST /extract ($0.001) │
├─▶ POST /screenshot ($0.001) │
├─▶ POST /metadata ($0.001) │
├─▶ POST /workflow ($0.001) │
├─▶ POST /session ($0.001) │
│ │
AI Agent ───────┼─▶ POST /mcp │
(MCP) │ • initialize │
│ • tools/list │
│ • tools/call (paid) │
│ │
└──────────────┬───────────────────┘
│
┌────────────────┴─────────────────┐
│ │
Coinbase CDP facilitator Browser Rendering API
(api.cdp.coinbase.com/ Groq API (Llama 4 Scout)
platform/v2/x402) KV (sessions, free tier)
Ed25519 JWT auth
Settles USDC on Base
│
▼
payTo wallet 0x3F33...9E9a
Stack:
withX402 payment bindingeip155:8453)0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913)api.cdp.coinbase.com/platform/v2/x402) with Ed25519 JWT authEvery wallet address gets 10 free calls per 30 days on the HTTP API. Pass your Base wallet in the X-402-Payer header. After 10 calls, payment via x402 is required.
Free tier is HTTP-only. MCP calls go through the standard x402 payment flow.
Launch window (first 48h on mainnet): $0.001 flat per tool call.
After validation, pricing ramps to:
| Tool | Production price |
|---|---|
scrape_webpage | $0.003 |
extract_structured_data | $0.005 |
screenshot_webpage | $0.003 |
extract_metadata | $0.002 |
run_workflow | $0.008 |
create_browser_session | $0.001 |
Bulk discounts (20% at 1K calls/month, 40% at 10K) are planned.
| Traditional API | x402 + MCP |
|---|---|
| Sign up at scraperapi.com | Discover via MCP initialize |
| Add credit card | Wallet holds USDC |
| Get API key | No keys |
| $49/month minimum | $0.001 per call |
| Manage rate limits | Pay-per-use, no limits |
| Human in the loop | Agent fully autonomous |
# Service identity
curl https://agent-scrape.healingsunhaven.workers.dev/ | jq .
# x402 manifest
curl https://agent-scrape.healingsunhaven.workers.dev/.well-known/x402 | jq .
# 402 challenge with x402 v2 headers
curl -i -X POST https://agent-scrape.healingsunhaven.workers.dev/scrape \
-H "Content-Type: application/json" \
-d '{"url":"https://example.com"}'
# → HTTP 402, Payment-Required header (base64 JSON), Cache-Control: private, no-store
# CORS preflight (browser-based agents)
curl -i -X OPTIONS https://agent-scrape.healingsunhaven.workers.dev/scrape \
-H "Origin: https://example.com" \
-H "Access-Control-Request-Method: POST" \
-H "Access-Control-Request-Headers: Content-Type,X-Payment"
# → HTTP 204, allow-headers includes X-Payment and Payment-Signature
Q3 2026:
langchain-agent-scrape)Q4 2026:
Requires Node 22+, a Cloudflare account with Workers + Browser Rendering enabled, a Groq API key, and a Coinbase CDP API key.
git clone https://github.com/hshintelligence/agent-scrape.git
cd agent-scrape
npm install
# Set secrets
npx wrangler secret put GROQ_API_KEY
npx wrangler secret put CDP_API_KEY_ID
npx wrangler secret put CDP_API_KEY_SECRET
# Local dev
npx wrangler dev
# Deploy
npx wrangler deploy
To use your own wallet as payTo, edit the PAY_TO constant in src/index.ts.
MIT — see LICENSE.
Built by HSH Intelligence, operated by Healing Sun Haven LLC (Wyoming, USA).
Pay-per-call web scraping for AI agents — no signup, no API keys, just USDC.
ElizaOS supports remote MCP servers natively via the @elizaos/plugin-mcp plugin. AgentScrape works out of the box — no custom integration needed.
bun add @elizaos/plugin-mcp
# or
npm install @elizaos/plugin-mcp
In your ElizaOS character JSON, add the plugin and point the MCP server config at AgentScrape's Streamable HTTP endpoint:
{
"name": "ResearchAgent",
"plugins": ["@elizaos/plugin-mcp"],
"settings": {
"mcp": {
"servers": {
"agentscrape": {
"type": "streamable-http",
"name": "AgentScrape",
"url": "https://agent-scrape.healingsunhaven.workers.dev/mcp",
"timeout": 60
}
}
}
}
}
Once configured, the agent automatically discovers all six AgentScrape tools:
| Tool | Cost | Purpose |
|---|---|---|
scrape_webpage | $0.003 USDC | Markdown/HTML/text/JSON scrape |
extract_structured_data | $0.005 USDC | AI extraction via Groq + Llama 4 Scout |
screenshot_webpage | $0.003 USDC | PNG screenshot with viewport control |
extract_metadata | $0.002 USDC | Title, OG, Twitter, JSON-LD |
create_browser_session | $0.001 USDC | Stateful browser session |
run_workflow | $0.008 USDC | Multi-step atomic workflow up to 20 steps |
The first 10 calls per wallet in the first 30 days are free. After that, calls are paid in USDC on Base mainnet (eip155:8453) via the x402 v2 payment protocol. To pay, supply the X-PAYMENT-RESPONSE header with an x402 payment receipt on retry — the standard x402 flow.
Once the plugin is wired up, your ElizaOS agent can use AgentScrape transparently:
User: "Scrape https://www.x402.org and give me a two-sentence summary."
ElizaOS routes the request through @elizaos/plugin-mcp, which calls AgentScrape's scrape_webpage tool, and the agent answers based on the live page content.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent