Website Contact & Social Extractor MCP server
tech.noahsarch/website-contact-extractornoahsarch.techstreamable-httpv0.1.1Scanned
Emails, phones, WhatsApp, social profiles and addresses from a website's public pages.
5 tools: 2 change things and 3 only read.
- Reads private data · 3
- Reads text others write · 3
- Can send data out · 4
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here change things. Govern them.
- 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 Website Contact & Social Extractor MCP server can do
The Website Contact & Social Extractor MCP server is published by noahsarch.tech, a domain the MCP Registry verified. It has 5 tools. It can create or change data (2 tools: extract_contacts_bulk and extract_from_html), but cannot delete data. 3 tools only read.
3 tools read private data (extract_contacts, find_social_profiles and check_url); 3 tools bring in text other people can write (extract_contacts, find_social_profiles and check_url); 4 tools can send data out of your system (extract_contacts, find_social_profiles, extract_contacts_bulk and 1 more). 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.
Last scanned Nov 13, 2026, version 0.1.1.
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.
5 tools
Changes things 2Claude Code: ask
extract_contacts_bulkOne call for a lead list: each site gets homepage + contact pages (max_pages), results per site plus a summary (sites with email/phone/WhatsApp, failures).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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it One call for a lead list: each site gets homepage + contact pages (max_pages), results per site plus a summary (sites with email/phone/WhatsApp, failures). Charged per page fetched across all sites. Example: urls ['a.com','b.ae'], max_pages 2, region 'AE'. Response: result with emails[] (email, source, role), phones[] (e164, international, region, type, source), whatsapp[], social{platform: [url, handle]}, addresses[], organization{}, pages[] (what was fetched, status) and summary{}, plus data_confidence, estimated_items[], sources[], data_version, warnings[] and a disclaimer. Charged per page actually fetched; failed fetches are free. URLs are not logged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
extract_from_htmlSame parser, no fetching: emails (incl.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Same parser, no fetching: emails (incl. obfuscated 'name [at] domain [dot] com'), phones, WhatsApp, social links, addresses, schema.org organisation data, and the contact-page links present. Free. Example: html '<a href="mailto:x@y.com">'. Response: result with emails[] (email, source, role), phones[] (e164, international, region, type, source), whatsapp[], social{platform: [url, handle]}, addresses[], organization{}, pages[] (what was fetched, status) and summary{}, plus data_confidence, estimated_items[], sources[], data_version, warnings[] and a disclaimer. Charged per page actually fetched; failed fetches are free. URLs are not logged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
Only reads 3Show 3 read-only tools
check_urlGET the URL (robots-respecting, public hosts only) and report status, final URL after redirects, content type, title, declared languages and whether a contact page is linked.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "contact": it reads contacts.
- untrusted-inputThe name "check_url" says "url": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "get" and "url": 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 GET the URL (robots-respecting, public hosts only) and report status, final URL after redirects, content type, title, declared languages and whether a contact page is linked. Use before a bulk job or to clean a URL list. Example: url 'example.com'. Response: result with emails[] (email, source, role), phones[] (e164, international, region, type, source), whatsapp[], social{platform: [url, handle]}, addresses[], organization{}, pages[] (what was fetched, status) and summary{}, plus data_confidence, estimated_items[], sources[], data_version, warnings[] and a disclaimer. Charged per page actually fetched; failed fetches are free. URLs are not logged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
extract_contactsFetch a site's homepage and up to max_pages-1 contact/about pages and return every email, phone (validated, E.164, type), WhatsApp link, social profile, postal address and organisa…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 name "extract_contacts" says "contact": it reads contacts.
- private-dataThe description's first sentence says "fetch" and "contact": it reads contacts.
- untrusted-inputThe description's first sentence says "fetch" and "email": it reads inbound email, which other people 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 site's homepage and up to max_pages-1 contact/about pages and return every email, phone (validated, E.164, type), WhatsApp link, social profile, postal address and organisation field found, with provenance per item. Example: url 'noahsarch.tech', max_pages 3, region 'AE'. Response: result with emails[] (email, source, role), phones[] (e164, international, region, type, source), whatsapp[], social{platform: [url, handle]}, addresses[], organization{}, pages[] (what was fetched, status) and summary{}, plus data_confidence, estimated_items[], sources[], data_version, warnings[] and a disclaimer. Charged per page actually fetched; failed fetches are free. URLs are not logged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
find_social_profilesHomepage only: Facebook, Instagram, X/Twitter, LinkedIn, YouTube, TikTok, Telegram, Snapchat, Pinterest, Threads, GitHub, TripAdvisor, Google Business links plus WhatsApp chat link…Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "find_social_profiles" says "find": a word for reading.
What it can reach
- private-dataThe description's first sentence says "thread": it reads messages.
- untrusted-inputThe description's first sentence says "thread": it reads messages, which other people 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 Homepage only: Facebook, Instagram, X/Twitter, LinkedIn, YouTube, TikTok, Telegram, Snapchat, Pinterest, Threads, GitHub, TripAdvisor, Google Business links plus WhatsApp chat links, with handles. Share buttons are excluded. Example: url 'https://example.com'. Response: result with emails[] (email, source, role), phones[] (e164, international, region, type, source), whatsapp[], social{platform: [url, handle]}, addresses[], organization{}, pages[] (what was fetched, status) and summary{}, plus data_confidence, estimated_items[], sources[], data_version, warnings[] and a disclaimer. Charged per page actually fetched; failed fetches are free. URLs are not logged.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: 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.
36 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 3 untrusted-input tools breaks every one.
- Reads private data3
- 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.
{
"permissions": {
"deny": [
"mcp__website-contact-extractor__check_url",
"mcp__website-contact-extractor__extract_contacts",
"mcp__website-contact-extractor__find_social_profiles"
]
}
}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 15, 2026, 13:23 UTC, unchanged since Oct 31, 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
- 2
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://contacts.noahsarch.tech/mcp: tools/list returned 5 tools to an anonymous client, including extract_contacts_bulk (write), extract_from_html (write)
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 0.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http website-contact-extractor https://contacts.noahsarch.tech/mcpclaude mcp add --transport http website-contact-extractor https://contacts.noahsarch.tech/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__website-contact-extractor__extract_contacts",
"mcp__website-contact-extractor__find_social_profiles",
"mcp__website-contact-extractor__extract_contacts_bulk",
"mcp__website-contact-extractor__extract_from_html",
"mcp__website-contact-extractor__check_url"
],
"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 website-contact-extractor. Review it before you use it.
Capability tags behind 4 rules
- mcp__website-contact-extractor__extract_contacts private-data, untrusted-input, outbound
- mcp__website-contact-extractor__find_social_profiles private-data, untrusted-input, outbound
- mcp__website-contact-extractor__extract_contacts_bulk outbound
- mcp__website-contact-extractor__check_url private-data, 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/tech.noahsarch/website-contact-extractor/verify?hash=2e9c03e1fe6aa9d36f267f36e31b0fcbb46f0805fdadab8845931a1050952056" | jq -e '.changed == false'Pinned hash 2e9c03e1fe6a, from Nov 13, 2026, 22:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/tech.noahsarch/website-contact-extractor/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/tech.noahsarch/website-contact-extractor)Source: MCP Registry. Synced Oct 31, 2026, 23:17 UTC.
Website Contact & Social Extractor MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Website Contact & Social Extractor MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 2 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 Website Contact & Social Extractor MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Website Contact & Social Extractor 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 Website Contact & Social Extractor MCP server have?
- 5 tools: 2 write, 3 read. extract_contacts_bulk, extract_from_html, extract_contacts, find_social_profiles and check_url.
Does the Website Contact & Social Extractor MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Website Contact & Social Extractor 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): extract_contacts, find_social_profiles, extract_contacts_bulk and check_url.
Has the Website Contact & Social Extractor MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.