AgentScrape MCP server
io.github.hshintelligence/agent-scrapehshintelligencestreamable-httpv0.6.1Scanned
Pay-per-call web scraping for AI agents via x402 on Base USDC. Six tools, no signup.
6 tools: 1 do something that can't be undone and 5 change things.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 4
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the AgentScrape MCP server can do
The AgentScrape MCP server is published by the GitHub account hshintelligence. It has 6 tools. It can do things that cannot be undone, such as sending, paying or publishing (screenshot_webpage) and create or change data (5 tools: scrape_webpage, extract_structured_data, extract_metadata, create_browser_session and 1 more), but cannot delete data. None of its tools only reads.
3 tools bring in text other people can write (scrape_webpage, screenshot_webpage and create_browser_session); 4 tools can send data out of your system (scrape_webpage, extract_structured_data, screenshot_webpage and 1 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 19, 2026, version 0.6.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
6 tools
Can't be undone 1Claude Code: ask
screenshot_webpageCapture a PNG screenshot of any webpage.Reads text others writeCan send data outNo 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.
What it can reach
- untrusted-inputThe name "screenshot_webpage" says "screenshot" and "webpage": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "capture" and "webpage": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
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.Reads text others writeNo findings
Why it is in this group
- The name "create_browser_session" says "create": a word for a change.
What it can reach
- untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
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.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
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.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
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.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe name "scrape_webpage" says "scrape": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
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.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:05 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (1 irreversible, 5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agent-scrape.healingsunhaven.workers.dev/mcp: tools/list returned 6 tools to an anonymous client, including screenshot_webpage (irreversible), scrape_webpage (write), extract_structured_data (write), extract_metadata (write), create_browser_session (write) and 1 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
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/mcpclaude mcp add --transport http agent-scrape https://agent-scrape.healingsunhaven.workers.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .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. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agent-scrape. Review it before you use it.
Capability tags behind 5 rules
- mcp__agent-scrape__scrape_webpage untrusted-input, outbound
- mcp__agent-scrape__extract_structured_data outbound
- mcp__agent-scrape__screenshot_webpage untrusted-input, outbound
- mcp__agent-scrape__extract_metadata outbound
- mcp__agent-scrape__create_browser_session untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.hshintelligence/agent-scrape/verify?hash=64a253caa3cb08716b4dfe9a1cbfd7c62ed9f46f91e7efbf5ed3579a7c47044a" | jq -e '.changed == false'Pinned hash 64a253caa3cb, from Nov 19, 2026, 21:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.hshintelligence/agent-scrape/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.hshintelligence/agent-scrape)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:36 UTC.
AgentScrape MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AgentScrape MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 6 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the AgentScrape MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AgentScrape MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: screenshot_webpage.
What tools does the AgentScrape MCP server have?
- 6 tools: 1 irreversible, 5 write. screenshot_webpage, scrape_webpage, extract_structured_data, extract_metadata, create_browser_session and run_workflow.
Does the AgentScrape MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AgentScrape MCP server send data to outside services?
- 4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): scrape_webpage, extract_structured_data, screenshot_webpage and extract_metadata.
Has the AgentScrape MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.