MCP server
AgentScrape
By hshintelligence
Pay-per-call web scraping for AI agents via x402 on Base USDC. Six tools, no signup.
Listed on
- Official MCP Registry
- Smithery
- Glamavia MCP Toplist
- PulseMCPvia MCP Toplist
First seen 2 Oct 2026. One server, whatever directories list it: each directory listing keeps its own page and history.
4
Directories
2 via MCP Toplist
6
Tools
From an anonymous probe
C
ToolBench grade
Arcade’s grade, not ours
2
GitHub stars
From MCP Toplist
Tools
| Tool | Description | Behaviour |
|---|---|---|
| create_browser_session | Create a stateful browser session that persists cookies and localStorage across multiple scrape/workflow calls. | Not declared |
| extract_metadata | Extract page metadata: title, description, Open Graph, Twitter cards, JSON-LD, canonical URL, and all meta tags. | Not declared |
| extract_structured_data | AI-powered structured data extraction from any webpage using natural language. Returns JSON matching your prompt or schema. | Not declared |
| run_workflow | Execute a multi-step browser workflow atomically: navigate, click, type, wait, scroll, screenshot, extract, evaluate. Up to 20 steps. | Not declared |
| scrape_webpage | Scrape any webpage and return content as markdown, html, text, or json. Pay-per-call web scraping for AI agents. | Not declared |
| screenshot_webpage | Capture a PNG screenshot of any webpage. Supports desktop, mobile, and tablet viewports, plus full-page mode. | Not declared |
| Directory | Listing | Tier | First seen |
|---|---|---|---|
| Official MCP Registry | AgentScrape | - | 2 Oct 2026 |
| Smithery | AgentScrape | - | 2 Oct 2026 |
| Glama | Listed there according to MCP Toplist’s dataset; not collected by InvokeRank. | ||
| PulseMCP | Listed there according to MCP Toplist’s dataset; not collected by InvokeRank. | ||