WebExtract MCP server
dev.webextract/extractwebextract.devstreamable-httpv1.0.4Scanned
Web page to structured JSON: product, tables, metadata. 20 free calls/day, x402.
2 tools: 2 only read.
- Reads private data · 1
- Reads text others write · 2
- Can send data out · 2
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 WebExtract MCP server can do
The WebExtract MCP server is published by webextract.dev, a domain the MCP Registry verified. It has 2 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool reads private data (extract_url); 2 tools bring in text other people can write (extract_url and page_markdown); 2 tools can send data out of your system (extract_url and page_markdown). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
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, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 9, 2026, version 1.0.4.
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.
2 tools
Only reads 2Show 2 read-only tools
extract_urlFetch a public web page (robots.txt respected) and return clean Markdown plus fixed-schema JSON: article metadata, product/price, tables.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- private-dataThe description's first sentence says "fetch" and "table": it reads databases.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "extract_url" says "url": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "fetch" and "web": 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.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Fetch a public web page (robots.txt respected) and return clean Markdown plus fixed-schema JSON: article metadata, product/price, tables. HTML only, no JS execution, no PDF. Free 20 calls/day per IP; pass 'Authorization: Bearer <key>' for prepaid credits.
Annotations the server declares
- title: Extract web page
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
page_markdownFetch a public web page (robots.txt respected) and return clean Markdown only.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "fetch" and "web": 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.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Fetch a public web page (robots.txt respected) and return clean Markdown only. HTML only, no JS execution, no PDF. Cheaper than extract_url (0.4 credit). Free 20 calls/day per IP; pass 'Authorization: Bearer <key>' for prepaid credits.
Annotations the server declares
- title: Web page to Markdown
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
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.
4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__extract__extract_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, 18:53 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
- 0
- 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
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.
Tools2 changed.~2 changedView diff
- Changed:extract_urlOnly readsdescription
- Changed:page_markdownOnly readsdescription
Tools2 changed.~2 changedView diff
- Changed:extract_urlOnly readsdescription
- Changed:page_markdownOnly readsdescription
Install
Pinned to version 1.0.4. Values in angle brackets are yours to fill in.
claude mcp add --transport http extract https://api.webextract.dev/mcpclaude mcp add --transport http extract https://api.webextract.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__extract__extract_url",
"mcp__extract__page_markdown"
],
"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 extract. Review it before you use it.
Capability tags behind 2 rules
- mcp__extract__extract_url private-data, untrusted-input, outbound
- mcp__extract__page_markdown untrusted-input, outbound
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/dev.webextract/extract/verify?hash=1cf8c561efc841a8394d565c51cfe3d5e1625d77241798b5d79aa2ed6d65c0a6" | jq -e '.changed == false'Pinned hash 1cf8c561efc8, from Nov 9, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.webextract/extract/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.webextract/extract)Source: MCP Registry · repository. Synced Nov 9, 2026, 14:18 UTC.
WebExtract MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the WebExtract MCP server safe?
- No scan can promise that. What its definitions show: 2 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the WebExtract MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the WebExtract MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the WebExtract MCP server have?
- 2 tools: 2 read. extract_url and page_markdown.
Does the WebExtract MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the WebExtract MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): extract_url and page_markdown.
Has the WebExtract MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.