mcpbeat

AgentScrape MCP Server

io.github.hshintelligence/agent-scrape
answering

AgentScrape is answering right now. Last checked 13 min ago. It exposes 6 tools. Last commit 22 Jun 2026.

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

Uptime history 39 hours of history
39 hours agonow
100.0%
Uptime 24h
91 of 91 checks
6
Tools
read from the server
127 ms
Response time
average over 24h
2
Stars
last commit 22 Jun 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

run in your terminal
claude mcp add agent-scrape --transport http https://agent-scrape.healingsunhaven.workers.dev/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "agent-scrape": {
      "url": "https://agent-scrape.healingsunhaven.workers.dev/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.agent-scrape]
url = "https://agent-scrape.healingsunhaven.workers.dev/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "agent-scrape": {
      "url": "https://agent-scrape.healingsunhaven.workers.dev/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "agent-scrape": {
      "url": "https://agent-scrape.healingsunhaven.workers.dev/mcp"
    }
  }
}

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

extract
extract_metadata
Extract page metadata: title, description, Open Graph, Twitter cards, JSON-LD, canonical URL, and all meta tags.
extract_structured_data
AI-powered structured data extraction from any webpage using natural language. Returns JSON matching your prompt or schema.
browser
create_browser_session
Create a stateful browser session that persists cookies and localStorage across multiple scrape/workflow calls.
scrape
scrape_webpage
Scrape any webpage and return content as markdown, html, text, or json. Pay-per-call web scraping for AI agents.
screenshot
screenshot_webpage
Capture a PNG screenshot of any webpage. Supports desktop, mobile, and tablet viewports, plus full-page mode.
workflow
run_workflow
Execute a multi-step browser workflow atomically: navigate, click, type, wait, scroll, screenshot, extract, evaluate. Up to 20 steps.

Endpoints

URLTransportStateLatencyChecked
https://agent-scrape.healingsunhaven.workers.dev/mcp streamable-http answering 380 ms 13 min ago

AgentScrape — questions

Answers built from our own checks of this server.

What can AgentScrape do?
It exposes 6 tools, read directly from the server on our last check. Among them: create_browser_session, extract_metadata, extract_structured_data, run_workflow, scrape_webpage, screenshot_webpage. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is AgentScrape working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 127 ms. The bar chart above shows every period we have measured.
How do I connect AgentScrape?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does AgentScrape need an API key?
No. AgentScrape completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is AgentScrape?
It answers our handshake in 127 ms on average, which is faster than 78% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is AgentScrape open source?
Yes — it is published under the MIT licence, written in TypeScript and 2 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.