Agent Scrape MCP Server
Live: agent-scrape.healingsunhaven.workers.dev. Its 6 documented tools cover webpage, extract. It is available as a remote MCP endpoint.
Teams that want a hosted browser automation endpoint instead of running a local process. The project is written in TypeScript.
VERIFIED ACTIVE
LAST COMMIT 2026-06-22 · ★ 2 · #188 OF 196 MAINTAINED BROWSER AUTOMATION · VERIFIED 2026-08-25
MIT · TypeScript servers · how we verify → /methodology
01 · Install Agent Scrape
before you install - you'll need
The README does not document required environment variables for a basic install.
Claude Code
claude mcp add hshintelligence-agent-scrape --transport http https://agent-scrape.healingsunhaven.workers.dev/mcp Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"hshintelligence-agent-scrape": {
"url": "https://agent-scrape.healingsunhaven.workers.dev/mcp"
}
}
} Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.
Using another client? Same JSON, different key
Claude Desktop · mcpServers
Cursor · mcpServers
VS Code · servers
Windsurf · mcpServers
Zed · context_servers
Cline · mcpServers
Roo Code · mcpServers
Continue · mcpServers
LibreChat · mcpServers
Gemini CLI · mcpServers
Codex CLI · mcp_servers
Full setup guides: every client.
02 · Evidence
https://agent-scrape.healingsunhaven.workers.dev/mcp
transport: streamable-http
endpoint alive - responded to MCP initialize · probed 2026-08-25
Security posture
What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.
runs as remote - your agent's requests go to agent-scrape.healingsunhaven.workers.dev
endpoint auth accepted our unauthenticated MCP initialize - no credentials needed to connect
license MIT - declared in the repository
registry namespace io.github.hshintelligence is GitHub-verified and matches the repo owner
03 · What Agent Scrape can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
What you can build
An agent gets 6 documented tools spanning webpage, extract, including scrape_webpage, extract_structured_data, screenshot_webpage, extract_metadata.
Capability map
Tools grouped from the project's README - what Agent Scrape lets an agent do.
Extract
2 tools - e.g. AI-powered structured extraction with natural-language prompts and JSON schemas (Groq + Llama 4 Scout); Title, description, Open Graph, Twitter cards, JSON-LD, canonical URL
extract_structured_data · extract_metadata
Scrape
1 tool - e.g. Scrape any URL to markdown, HTML, text, or JSON
scrape_webpage
Screenshot
1 tool - e.g. PNG screenshot with viewport control (desktop/mobile/tablet, optional full-page)
screenshot_webpage
create & write
1 tool - e.g. Stateful browser session with cookie + localStorage persistence
create_browser_session
run & execute
1 tool - e.g. Multi-step atomic execution: navigate, click, type, wait, scroll, screenshot, extract, evaluate
run_workflow
Latest releases
v0.6.1 · 2026-05-26
First tagged release. · Includes: · All 6 MCP tools: scrape_webpage, extract_structured_data, screenshot_webpage, extract_metadata, create_browser_session, run_workflow · x402 v2 payment gate via Coinbase CDP…
04 · Who maintains Agent Scrape
AgentScrape is maintained by hshintelligence. We track 2 MCP servers from hshintelligence - 2 actively maintained, 3 combined GitHub stars, oldest repo from May 2026.
05 · Facts
- repository
- github.com/hshintelligence/agent-scrape
- category
- browser automation - ranked #188 of 196 actively-maintained browser automation servers as of 2026-08-25.
- registry
- io.github.hshintelligence/agent-scrape (active, first published 2026-05-27)
06 · Agent Scrape FAQ
Is Agent Scrape still maintained?
Yes - as of 2026-08-25, its last commit was 2026-06-22. We re-verify nightly.
What can Agent Scrape do?
An agent gets 6 documented tools spanning webpage, extract, including scrape_webpage, extract_structured_data, screenshot_webpage, extract_metadata.
How do I install Agent Scrape?
Run `claude mcp add hshintelligence-agent-scrape --transport http https://agent-scrape.healingsunhaven.workers.dev/mcp`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.
Does Agent Scrape require authentication?
No - the endpoint accepted our unauthenticated MCP initialize when probed on 2026-08-25; you can connect without credentials.
07 · Alternatives to Agent Scrape
Alternatives to Agent Scrape
Maintained browser automation servers if Agent Scrape isn't the fit.
- Chrome DevTools MCP MCP server for Chrome DevTools ★ 49,617 · 2026-08-23
- Server Browser MCP server for browser use access ★ 38,704 · 2026-08-05
- Playwright MCP Playwright Tools for MCP ★ 36,436 · 2026-08-21
- Mobile MCP MCP server for iOS and Android Mobile Development, Automation and Testing ★ 5,995 · 2026-08-18
- Agent Device (callstack) MCP server for mobile app automation: verify, control, and debug iOS, Android, TV, and desktop apps ★ 4,212 · 2026-08-24
- Agent Device (callstackincubator) Let AI agents inspect, control, and debug real iOS, Android, desktop, and TV apps ★ 4,211 · 2026-08-24
Pairs well with
Servers that cover what Agent Scrape doesn't - only shown when the pairing reason fits the companion.
- Firecrawl MCP Server → web scraping companion web scraping · ★ 7,310
- Tavily MCP → web scraping companion web scraping · ★ 2,351
- Codebase Memory → memory companion memory · ★ 40,198
- Memorix → memory companion memory · ★ 688
- Server Filesystem → filesystem companion filesystem · ★ 38,704
- X402 List MCP → filesystem companion filesystem · ★ 58
More browser automation MCP servers · Onsense · Dejared · Smartest Tv · X Use · adb-MCP - Android emulator and device control over adb
More TypeScript MCP servers · Httpayer MCP Server · Feishu Markdown MCP · Reunion · Xahau MCP · Code Cartographer · see all