ZadenWorks MCP server
io.github.ZadenGG/x402-zadenworksZadenGGstreamable-httpv2.1.0Scanned
Read, screenshot, diff, verify and audit any URL: SEO, links, sitemaps, schema, a11y.
20 tools: 13 change things and 7 only read.
- Reads private data · 1
- Reads text others write · 2
- Can send data out · 12
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
13 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 ZadenWorks MCP server can do
The ZadenWorks MCP server is published by the GitHub account ZadenGG. It has 20 tools. It can create or change data (13 tools: watch_page, batch_pages, verify_claim, extract_tables and 9 more), but cannot delete data. 7 tools only read.
1 tool reads private data (find_contacts); 2 tools bring in text other people can write (read_page and find_contacts); 12 tools can send data out of your system (read_page, watch_page, verify_claim and 9 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, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 16, 2026, version 2.1.0.
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.
20 tools
Changes things 13Claude Code: ask
audit_seoAudit the on-page SEO fundamentals search engines and social platforms actually read: title and meta-description length, canonical tag, Open Graph and Twitter Card tags, heading st…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.urls): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Audit the on-page SEO fundamentals search engines and social platforms actually read: title and meta-description length, canonical tag, Open Graph and Twitter Card tags, heading structure, robots directives, viewport, and whether robots.txt and sitemap.xml exist. Returns a prioritised plain-English issue list and a 0-100 score per URL. Takes up to 10 URLs in one call, so competitors can be audited alongside your own page. No browser is used, so it is fast. Paid: $0.01 per call in USDC on Base via x402 — call once without x_payment to receive the payment challenge.
audit_site_healthRun a COMPLETE health check on a page behind a single payment, and the tool to reach for when someone asks 'is this page any good?' rather than one narrow question.Can send data outNo findings
Why it is in this group
- The description's first verb is "run": a word for a change.
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 Run a COMPLETE health check on a page behind a single payment, and the tool to reach for when someone asks 'is this page any good?' rather than one narrow question. Covers on-page SEO and meta tags, JSON-LD structured data and social preview tags, and WCAG accessibility -- optionally plus broken links and robots.txt/sitemap crawlability. Returns one overall score, every finding in a single worst-first list with the check that produced it, and the full per-check detail. Cheaper and far simpler than calling audit_seo, validate_structured_data and scan_accessibility separately and paying three times. Paid: $0.05 per call in USDC on Base via x402 -- call once without x_payment to receive the payment challenge.
audit_sitemapAudit a site's crawlability from robots.txt and its XML sitemaps: whether robots.txt exists, whether it blocks all crawlers, which sitemaps it declares, whether those parse as vali…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.
Description, as the server wrote it Audit a site's crawlability from robots.txt and its XML sitemaps: whether robots.txt exists, whether it blocks all crawlers, which sitemaps it declares, whether those parse as valid XML, how many URLs they list, whether entries carry lastmod dates, and whether a live sample of those URLs actually respond. Returns a 0-100 score, a letter grade, a severity and a prioritised issue list. Accepts a bare domain. Up to 2 sites per call. Paid: $0.02 per call in USDC on Base via x402 -- call once without x_payment to receive the payment challenge.
batch_pagesRun a mix of read_page/watch_page/verify_claim/compare_pages/extract_tables operations behind a SINGLE payment instead of paying for each one separately — use this whenever you nee…No findings
Why it is in this group
- The description's first verb is "run": a word for a change.
Description, as the server wrote it Run a mix of read_page/watch_page/verify_claim/compare_pages/extract_tables operations behind a SINGLE payment instead of paying for each one separately — use this whenever you need to process more than one URL, since it saves you multiple payment negotiations. Each item needs an 'op' ("read", "watch", "verify", "compare", or "tables") plus that op's required fields (url for read/watch/verify/tables, urlA+urlB for compare, claim for verify). Sized by weight, not item count: read/watch/verify/tables = 1 unit each, compare = 2 units (it loads two pages); total weight per call must be ≤ 6. Paid: $0.05 flat per call (a discount vs paying per-item) in USDC on Base via x402 — call once without x_payment to receive the payment challenge.
check_email_dnsGrade a domain's email authentication from DNS -- the tool to reach for when mail is landing in spam, or someone asks whether a domain is protected against spoofing.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.
Description, as the server wrote it Grade a domain's email authentication from DNS -- the tool to reach for when mail is landing in spam, or someone asks whether a domain is protected against spoofing. Checks MX (can it receive mail), SPF (who may send as it, and whether '+all' lets anyone), DMARC policy (none / quarantine / reject) and DKIM under the common selectors. Returns a 0-100 score, a letter grade, the records found and a prioritised issue list. Up to 4 domains per call. Paid: $0.01 per call in USDC on Base via x402 -- call once without x_payment to receive the payment challenge.
check_linksCheck every link on a page and report which are broken.Can send data outNo findings
Why it is in this group
- The name "check_links" says "link": a word for a change.
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 Check every link on a page and report which are broken. Each anchor is resolved to an absolute URL, de-duplicated, and checked with a HEAD request (falling back to GET where the server rejects HEAD), returning its status code, whether it redirected, response time and a severity. Gives a 0-100 score and a letter grade per page. Anchors, mailto: and tel: links are excluded because they cannot be broken. Up to 5 pages and 40 link checks per call. Paid: $0.02 per call in USDC on Base via x402 — call once without x_payment to receive the payment challenge.
detect_tech_stackDetect what a website is built with: CMS, ecommerce platform, JS framework, analytics and tag managers, marketing automation, chat widget, payment provider, CDN and hosting, CSS fr…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.urls): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Detect what a website is built with: CMS, ecommerce platform, JS framework, analytics and tag managers, marketing automation, chat widget, payment provider, CDN and hosting, CSS framework. Also flags vendor risks -- legacy jQuery 1.x, a CMS generator tag exposing its exact version, mixed content. Useful for sales prospecting, competitor research and security triage. Up to 10 sites per call. Paid: $0.01 per call in USDC on Base via x402 -- call once without x_payment to receive the payment challenge.
extract_tablesExtract every HTML table on a page as structured JSON — headers, row arrays, and (when headers exist and are unique) row objects keyed by header name, plus a best-effort caption fo…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 every HTML table on a page as structured JSON — headers, row arrays, and (when headers exist and are unique) row objects keyed by header name, plus a best-effort caption for each table. Saves hand-parsing pricing tables, spec sheets, and schedules out of raw HTML. Paid: $0.01 per call in USDC on Base via x402 — call once without x_payment to receive the payment challenge.
render_urlRender any public URL in a real headless browser and get back a screenshot (PNG image), PDF, or the JavaScript-rendered HTML.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 Render any public URL in a real headless browser and get back a screenshot (PNG image), PDF, or the JavaScript-rendered HTML. Paid: $0.02 per call in USDC on Base via x402 — call once without x_payment to receive the payment challenge.
scan_accessibilityQuick WCAG-oriented accessibility scan of a page's markup: images with no alt attribute, form fields with no accessible label, a missing lang or viewport, links with no accessible …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.urls): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Quick WCAG-oriented accessibility scan of a page's markup: images with no alt attribute, form fields with no accessible label, a missing lang or viewport, links with no accessible name, duplicate ids, and skipped heading levels. Returns a 0-100 score, a letter grade, a severity and a prioritised issue list. This is STATIC analysis of the served HTML, so it does not check colour contrast, focus order, keyboard traps or runtime ARIA state -- the response names those exclusions explicitly rather than implying they passed. Up to 10 URLs per call. Paid: $0.01 per call in USDC on Base via x402 -- call once without x_payment to receive the payment challenge.
sec_filingsA US public company's recent SEC EDGAR filings, newest first -- the tool to reach for when someone asks what a company has filed lately, wants its latest 10-K or 10-Q, or needs rec…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.
Description, as the server wrote it A US public company's recent SEC EDGAR filings, newest first -- the tool to reach for when someone asks what a company has filed lately, wants its latest 10-K or 10-Q, or needs recent 8-K events (earnings, executive changes, acquisitions; the 8-K item codes are included). Companies by ticker (AAPL) or CIK, up to 5 per call; form types default to 8-K, 10-Q and 10-K but any can be named (S-1, DEF 14A, SC 13D ...). Returns filing and report dates and direct links to the filing index and primary document. Paid: $0.01 per call in USDC on Base via x402 -- call once without x_payment to receive the payment challenge.
verify_claimCheck whether a claimed quote or fact actually appears on a URL — a cheap citation/hallucination checker.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 Check whether a claimed quote or fact actually appears on a URL — a cheap citation/hallucination checker. Returns verdict exact_match, close_match (with a confidence score and the closest matching passage), or not_found. Paid: $0.01 per call in USDC on Base via x402 — call once without x_payment to receive the payment challenge.
watch_pageCheck whether a URL's content has changed since the last check (paragraph-level diff).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 Check whether a URL's content has changed since the last check (paragraph-level diff). First call for a URL establishes a baseline (changed comes back null); later calls report true/false plus what was added or removed. Baselines are shared across callers by default for the same URL — pass a unique 'key' for a private baseline. Paid: $0.01 per call in USDC on Base via x402 — call once without x_payment to receive the payment challenge.
Only reads 7Show 7 read-only tools
compare_pagesCompare two URLs' content and report what's different: paragraphs unique to each side, word count delta, whether they're identical.No findings
Why it is in this group
- The name "compare_pages" says "compare": a word for reading.
Description, as the server wrote it Compare two URLs' content and report what's different: paragraphs unique to each side, word count delta, whether they're identical. Paid: $0.02 per call in USDC on Base via x402 — call once without x_payment to receive the payment challenge.
find_contactsFind a company website's public contact details -- the tool to reach for when someone needs an email address, phone number or social profile for a business.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "find_contacts" says "find": a word for reading.
What it can reach
- private-dataThe name "find_contacts" says "find" and "contact": it reads contacts.
- private-dataThe description's first sentence says "find" and "contact": it reads contacts.
- untrusted-inputThe description's first sentence says "find" and "website": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.urls), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.urls): 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 Find a company website's public contact details -- the tool to reach for when someone needs an email address, phone number or social profile for a business. Reads the homepage plus up to three likely pages (/contact, /about ...) and returns email addresses (including Cloudflare-obfuscated ones), phone numbers, social profiles (LinkedIn, X/Twitter, Facebook, Instagram, YouTube, TikTok, GitHub) and the contact page URL. Up to 5 sites per call; a site behind a bot-protection challenge is reported as blocked, never guessed. Paid: $0.02 per call in USDC on Base via x402 -- call once without x_payment to receive the payment challenge.
list_rank_categoriesList the currently available x402 service ranking categories.No findings
Why it is in this group
- The name "list_rank_categories" says "list": a word for reading.
Description, as the server wrote it List the currently available x402 service ranking categories. Free, no payment required.
lookup_domainLook up domain registration over RDAP (the ICANN successor to WHOIS) -- the tool to reach for when someone asks when a domain expires, who its registrar is, or whether it is regist…No findings
Why it is in this group
- The name "lookup_domain" says "lookup": a word for reading.
Description, as the server wrote it Look up domain registration over RDAP (the ICANN successor to WHOIS) -- the tool to reach for when someone asks when a domain expires, who its registrar is, or whether it is registered at all. Returns the registrar, creation and expiry dates, days until expiry, EPP status codes (e.g. clientTransferProhibited) and nameservers, with isExpired / isExpiringSoon flags, a 0-100 score and a one-line summary. Up to 10 domains per call; URLs and www. are stripped. A TLD with no RDAP service is reported as a failed lookup with the reason, never guessed. Paid: $0.01 per call in USDC on Base via x402 -- call once without x_payment to receive the payment challenge.
rank_x402_servicesGet a ranked list of the best x402 pay-per-call services for a task category (scored by price, usage volume, and recency, from the live Coinbase Bazaar feed).No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get a ranked list of the best x402 pay-per-call services for a task category (scored by price, usage volume, and recency, from the live Coinbase Bazaar feed). Use list_rank_categories first to see valid categories. Paid: $0.02 per call in USDC on Base via x402 — call once without x_payment to receive the payment challenge.
read_pageExtract clean readable markdown/text from any public URL (title, byline, excerpt, body content with nav/ads/scripts stripped).Reads text others writeCan send data outNo findings
Why it is in this group
- The name "read_page" says "read": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "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 Extract clean readable markdown/text from any public URL (title, byline, excerpt, body content with nav/ads/scripts stripped). Handles JS-rendered pages. Paid: $0.01 per call in USDC on Base via x402 — call once without x_payment to receive the payment challenge.
validate_structured_dataValidate a page's JSON-LD structured data and its social preview tags.Can send data outNo findings
Why it is in this group
- The name "validate_structured_data" says "validate": a word for reading.
What it can reach
- outboundThe input takes a URL (input.urls): 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 Validate a page's JSON-LD structured data and its social preview tags. Reports which schema.org types are present, whether each carries the fields Google's rich results require, whether any JSON-LD block fails to parse as JSON, and whether Open Graph and Twitter Card tags are complete. Useful before publishing, or to diagnose why a page renders no preview card when shared. Returns a 0-100 score, a letter grade and a prioritised issue list. Up to 10 URLs per call. Paid: $0.01 per call in USDC on Base via x402 -- call once without x_payment to receive the payment challenge.
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.
24 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 out12
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__x402-zadenworks__find_contacts"
]
}
}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, 19:01 UTC, unchanged since Oct 29, 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
- 13
- 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 13 tools that change things (13 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://x402-zadenworks.zaden-gaming.workers.dev/mcp: tools/list returned 20 tools to an anonymous client, including watch_page (write), batch_pages (write), verify_claim (write), extract_tables (write), audit_seo (write) and 8 more
Posture changes
- Oct 29, 2026
- Tools that change things, listed without credentials: 10 to 13
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.
Tools4 added.+4 addedView diff
- Added:check_email_dnsChanges things
- Added:detect_tech_stackChanges things
- Added:find_contactsOnly reads
- Added:sec_filingsChanges things
PostureRemote posture changed. Tools that change things, listed without credentials: 10 -> 13.View diff
- Tools that change things, listed without credentials: 10 to 13
Install
Pinned to version 2.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http x402-zadenworks https://x402-zadenworks.zaden-gaming.workers.dev/mcpclaude mcp add --transport http x402-zadenworks https://x402-zadenworks.zaden-gaming.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": [
"mcp__x402-zadenworks__compare_pages",
"mcp__x402-zadenworks__lookup_domain",
"mcp__x402-zadenworks__rank_x402_services",
"mcp__x402-zadenworks__list_rank_categories"
],
"ask": [
"mcp__x402-zadenworks__read_page",
"mcp__x402-zadenworks__watch_page",
"mcp__x402-zadenworks__batch_pages",
"mcp__x402-zadenworks__verify_claim",
"mcp__x402-zadenworks__extract_tables",
"mcp__x402-zadenworks__audit_seo",
"mcp__x402-zadenworks__check_links",
"mcp__x402-zadenworks__audit_sitemap",
"mcp__x402-zadenworks__validate_structured_data",
"mcp__x402-zadenworks__scan_accessibility",
"mcp__x402-zadenworks__find_contacts",
"mcp__x402-zadenworks__detect_tech_stack",
"mcp__x402-zadenworks__check_email_dns",
"mcp__x402-zadenworks__sec_filings",
"mcp__x402-zadenworks__audit_site_health",
"mcp__x402-zadenworks__render_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 x402-zadenworks. Review it before you use it.
Capability tags behind 12 rules
- mcp__x402-zadenworks__read_page untrusted-input, outbound
- mcp__x402-zadenworks__watch_page outbound
- mcp__x402-zadenworks__verify_claim outbound
- mcp__x402-zadenworks__extract_tables outbound
- mcp__x402-zadenworks__audit_seo outbound
- mcp__x402-zadenworks__check_links outbound
- mcp__x402-zadenworks__validate_structured_data outbound
- mcp__x402-zadenworks__scan_accessibility outbound
- mcp__x402-zadenworks__find_contacts private-data, untrusted-input, outbound
- mcp__x402-zadenworks__detect_tech_stack outbound
- mcp__x402-zadenworks__audit_site_health outbound
- mcp__x402-zadenworks__render_url 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/io.github.ZadenGG/x402-zadenworks/verify?hash=ca048c9718973e34176964db4d56c7d423b3c8e7c8d5d239dc24cc6956779bbf" | jq -e '.changed == false'Pinned hash ca048c971897, from Nov 16, 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.ZadenGG/x402-zadenworks/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.ZadenGG/x402-zadenworks)Source: MCP Registry. Synced Oct 21, 2026, 18:22 UTC.
ZadenWorks MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ZadenWorks MCP server safe?
- No scan can promise that. What its definitions show: 20 tools, 13 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 ZadenWorks MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ZadenWorks 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 ZadenWorks MCP server have?
- 20 tools: 13 write, 7 read. watch_page, batch_pages, verify_claim, extract_tables, audit_seo, check_links, audit_sitemap, scan_accessibility and 12 more.
Does the ZadenWorks MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ZadenWorks MCP server send data to outside services?
- 12 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): read_page, watch_page, verify_claim, extract_tables, audit_seo, check_links and 6 more.
Has the ZadenWorks MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 3, 2026. Every change is on this page and in its Atom feed.