Claude MarketplacesSubmit
hshintelligence avatar

AgentScrape

hshintelligence/agent-scrape

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.

GitHub stars
1
tools
6
transport
HTTP
last updated
May 27, 2026
View on GitHub

Install

From registry metadata
$ npx add-mcp https://agent-scrape.healingsunhaven.workers.dev/mcp --name agent-scrape

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http agent-scrape https://agent-scrape.healingsunhaven.workers.dev/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 6 tools

Verified live against the running server on Nov 6, 2026.

scrape_webpageScrape any webpage and return content as markdown, html, text, or json. Pay-per-call web scraping for AI agents.5 params

Scrape any webpage and return content as markdown, html, text, or json. Pay-per-call web scraping for AI agents.

Parameters* required
formatstring
Output format (default: markdown)one of markdown · html · text · json
url*string
The URL to scrape (http or https)
viewportstring
Viewport size (default: desktop)one of desktop · mobile · tablet
wait_forstring
CSS selector to wait for before extracting
wait_msnumber
Milliseconds to wait after page load (max 10000)
extract_structured_dataAI-powered structured data extraction from any webpage using natural language. Returns JSON matching your prompt or schema.5 params

AI-powered structured data extraction from any webpage using natural language. Returns JSON matching your prompt or schema.

Parameters* required
prompt*string
Natural language description of what to extract
schemaobject
Optional JSON schema for the response
url*string
The URL to extract from
wait_forstring
wait_msnumber
screenshot_webpageCapture a PNG screenshot of any webpage. Supports desktop, mobile, and tablet viewports, plus full-page mode.5 params

Capture a PNG screenshot of any webpage. Supports desktop, mobile, and tablet viewports, plus full-page mode.

Parameters* required
full_pageboolean
Capture full scrollable page (default: false)
url*string
viewportstring
one of desktop · mobile · tablet
wait_forstring
wait_msnumber
extract_metadataExtract page metadata: title, description, Open Graph, Twitter cards, JSON-LD, canonical URL, and all meta tags.1 params

Extract page metadata: title, description, Open Graph, Twitter cards, JSON-LD, canonical URL, and all meta tags.

Parameters* required
url*string
create_browser_sessionCreate a stateful browser session that persists cookies and localStorage across multiple scrape/workflow calls.1 params

Create a stateful browser session that persists cookies and localStorage across multiple scrape/workflow calls.

Parameters* required
ttl_secondsnumber
Session TTL (default 1800, max 7200)
run_workflowExecute a multi-step browser workflow atomically: navigate, click, type, wait, scroll, screenshot, extract, evaluate. Up to 20 steps.4 params

Execute a multi-step browser workflow atomically: navigate, click, type, wait, scroll, screenshot, extract, evaluate. Up to 20 steps.

Parameters* required
persist_sessionboolean
session_idstring
steps*array
Ordered list of workflow steps to execute
viewportstring
one of desktop · mobile · tablet

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

Details

Repository
github.com/hshintelligence/agent-scrape
Website
agent-scrape.healingsunhaven.workers.dev
Categories
AI & LLM Tools, Search & Web Crawling
Transport
HTTP
Registry
MCP registry, active
Tools verified
Nov 6, 2026

More from hshintelligence

Related AI & LLM Tools MCP servers

View all
1dingdawg avatarDingdawg Data Agentdingdawg/dingdawg-agent-1AI data agent — schema analysis, query optimization, PII detection, pipelines.0stars
2dingdawg avatarDingdawg Devops Agentdingdawg/dingdawg-agent-1DevOps AI. Deploy checks, incident analysis, infra audit. Learns from past failures.0stars
3dingdawg avatarDingdawg Marketing Agentdingdawg/dingdawg-agent-1AI content generation, SEO audits, campaign planning & social scheduling.0stars
4dingdawg avatarDingdawg Planning Agentdingdawg/dingdawg-agent-1Planning AI. Sprint estimation, task breakdown, risk analysis. Learns your velocity.0stars
5dingdawg avatarDingdawg Sales Agentdingdawg/dingdawg-agent-1AI prospect research, outreach drafting, lead scoring & pipeline tracking.0stars
6serpstatglobal avatarLLM Brand Monitorserpstatglobal/llm-brand-monitor-mcpTrack how 350+ AI models mention your brand — manage projects, run scans, analyze results1stars