Skip to content

AgentScrape

by hshintelligence · remote · no sign-in to list tools · v0.6.1 · published by GitHub user hshintelligence

Pay-per-call web scraping for AI agents via x402 on Base USDC. Six tools, no signup.

Final · 1Changes · 5
CompareRegistry entry

6 tools: 1 do something that can't be undone and 5 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

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

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

6 tools

Can't be undone 1Claude Code: ask
  • screenshot_webpageCapture a PNG screenshot of any webpage.No findings

    Why it is in this group

    • The name "screenshot_webpage" says "screenshot": a word for reading.
    • The description's first verb is "capture": a word that usually means money moves, which cannot be taken back.
    Description, as the server wrote it
    Capture a PNG screenshot of any webpage. Supports desktop, mobile, and tablet viewports, plus full-page mode.

    Annotations the server declares

    • title: Screenshot Webpage
Changes things 5Claude Code: ask
  • create_browser_sessionCreate a stateful browser session that persists cookies and localStorage across multiple scrape/workflow calls.No findings

    Why it is in this group

    • The name "create_browser_session" says "create": a word for a change.
    Description, as the server wrote it
    Create a stateful browser session that persists cookies and localStorage across multiple scrape/workflow calls.

    Annotations the server declares

    • title: Create Browser Session
  • extract_metadataExtract page metadata: title, description, Open Graph, Twitter cards, JSON-LD, canonical URL, and all meta tags.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Extract page metadata: title, description, Open Graph, Twitter cards, JSON-LD, canonical URL, and all meta tags.

    Annotations the server declares

    • title: Extract Page Metadata
  • extract_structured_dataAI-powered structured data extraction from any webpage using natural language.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    AI-powered structured data extraction from any webpage using natural language. Returns JSON matching your prompt or schema.

    Annotations the server declares

    • title: Extract Structured Data
  • run_workflowExecute a multi-step browser workflow atomically: navigate, click, type, wait, scroll, screenshot, extract, evaluate.No findings

    Why it is in this group

    • The name "run_workflow" says "run": a word for a change.
    Description, as the server wrote it
    Execute a multi-step browser workflow atomically: navigate, click, type, wait, scroll, screenshot, extract, evaluate. Up to 20 steps.

    Annotations the server declares

    • title: Run Browser Workflow
  • scrape_webpageScrape any webpage and return content as markdown, html, text, or json.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Scrape any webpage and return content as markdown, html, text, or json. Pay-per-call web scraping for AI agents.

    Annotations the server declares

    • title: Scrape Webpage

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.6.1. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__agent-scrape__scrape_webpage",
      "mcp__agent-scrape__extract_structured_data",
      "mcp__agent-scrape__screenshot_webpage",
      "mcp__agent-scrape__extract_metadata",
      "mcp__agent-scrape__create_browser_session",
      "mcp__agent-scrape__run_workflow"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as agent-scrape. Review it before you use it.