Skip to content

P0: CVE, package and domain checks MCP server

dev.workers.x402-bazaar-rank-worker.x402-bazaar-rank/cve-package-domain-securityx402-bazaar-rank.x402-bazaar-rank-worker.workers.devstreamable-httpv1.0.2Scanned

CVE with EPSS and CISA KEV, package risk, software EOL, domain and IP reports, pay per call

9 tools: 8 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 8 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 9
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

8 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the P0: CVE, package and domain checks MCP server can do

The P0: CVE, package and domain checks MCP server is published by x402-bazaar-rank.x402-bazaar-rank-worker.workers.dev, a domain the MCP Registry verified. It has 9 tools. It can create or change data (8 tools: vuln_cve, vuln_kev_new, package_risk, software_eol and 4 more), but cannot delete data. 1 tool only reads.

9 tools bring in text other people can write (vuln_cve, vuln_kev_new, package_risk and 6 more); 1 tool can send data out of your system (site_snapshot).

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 13, 2026, version 1.0.2.

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.

9 tools

Changes things 8Claude Code: ask
  • check_infraUse when you need to check infrastructure in one call: any combination (at least one) of ip (ASN, Tor exit, cloud range), domain (status, TLS, robots), cve (CVSS, EPSS, CISA KEV).Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use when you need to check infrastructure in one call: any combination (at least one) of ip (ASN, Tor exit, cloud range), domain (status, TLS, robots), cve (CVSS, EPSS, CISA KEV). Returns the paid x402 request for your input (GET /check/infra, $0.015 per call; schema linked). Call that URL with an x402 or MPP client to get the data. Bad input is refused before any charge. For one input use ip_passport, vuln_cve, package_risk or software_eol; for DNS, SPF, DMARC and registration use domain_report; for sitemap or WordPress use site_snapshot. First call each day returns the data itself, free; later calls return the paid request.

    Annotations the server declares

    • title: Check infra
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • domain_reportUse when you need one report on a domain: DNS records (A, AAAA, MX, NS, TXT, CAA) with SPF and DMARC parsed, RDAP registration for .com, .net and .org (registrar, dates, status, na…Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use when you need one report on a domain: DNS records (A, AAAA, MX, NS, TXT, CAA) with SPF and DMARC parsed, RDAP registration for .com, .net and .org (registrar, dates, status, nameservers, DNSSEC). Returns the paid x402 request for your input (GET /domain/report, $0.005 per call; schema linked). Call that URL with an x402 or MPP client to get the data. Bad input is refused before any charge. For several domains use domain_report_batch. First call each day returns the data itself, free; later calls return the paid request.

    Annotations the server declares

    • title: Domain report
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • domain_report_batchUse when you need to vet several domains at once (vendors, leads, lookalikes): up to 10 domains in one POST, each answered exactly like /domain/report.Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use when you need to vet several domains at once (vendors, leads, lookalikes): up to 10 domains in one POST, each answered exactly like /domain/report. Returns the paid x402 request for your input (POST /domain/report/batch, $0.05 per call; schema linked). POST that JSON body to the URL with an x402 or MPP client to get the data. Bad input is refused before any charge. For one domain use domain_report. First call each day returns the data itself, free; later calls return the paid request.

    Annotations the server declares

    • title: Domain report batch
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • ip_passportUse when you need to profile an IP address in one call: ASN, AS name and country of its announced range, whether it is a current Tor exit node, and whether it lies in a public clou…Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use when you need to profile an IP address in one call: ASN, AS name and country of its announced range, whether it is a current Tor exit node, and whether it lies in a public cloud range. Returns the paid x402 request for your input (GET /ip/passport, $0.003 per call; schema linked). Call that URL with an x402 or MPP client to get the data. Bad input is refused before any charge. One public IP only (private and reserved addresses are refused before any charge); to check it together with a domain, CVE, package or software version in one call use check_infra. First call each day returns the data itself, free; later calls return the paid request.

    Annotations the server declares

    • title: IP passport
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • package_riskUse when you need to vet a dependency before installing or shipping it: pass ecosystem (npm, PyPI, Go, crates.io, RubyGems, Maven, NuGet).Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use when you need to vet a dependency before installing or shipping it: pass ecosystem (npm, PyPI, Go, crates.io, RubyGems, Maven, NuGet). Returns the paid x402 request for your input (GET /package/risk, $0.005 per call; schema linked). Call that URL with an x402 or MPP client to get the data. Bad input is refused before any charge. One exact package version. For a single CVE id use vuln_cve; to know whether a product or runtime version is still supported use software_eol. First call each day returns the data itself, free; later calls return the paid request.

    Annotations the server declares

    • title: Package risk
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • software_eolUse when you need to know if a software version is still supported: pass product (python, nodejs, ubuntu, postgresql, ...) and version (3.8.10) for its release cycle, end-of-life d…Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use when you need to know if a software version is still supported: pass product (python, nodejs, ubuntu, postgresql, ...) and version (3.8.10) for its release cycle, end-of-life date. Returns the paid x402 request for your input (GET /software/eol, $0.002 per call; schema linked). Call that URL with an x402 or MPP client to get the data. Bad input is refused before any charge. Support and end-of-life status only; for known vulnerabilities of a package version use package_risk, of a CVE id use vuln_cve. First call each day returns the data itself, free; later calls return the paid request.

    Annotations the server declares

    • title: Software eol
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • vuln_cveUse when you need to triage a CVE: description, CVSS per publisher, dates, CWE, key references, affected products, CISA SSVC, FIRST EPSS with a 30-day series and CISA KEV status in…Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use when you need to triage a CVE: description, CVSS per publisher, dates, CWE, key references, affected products, CISA SSVC, FIRST EPSS with a 30-day series and CISA KEV status in one call. Returns the paid x402 request for your input (GET /vuln/cve, $0.005 per call; schema linked). Call that URL with an x402 or MPP client to get the data. Bad input is refused before any charge. One CVE id. For CVEs newly added to CISA KEV since a date use vuln_kev_new; for the vulnerabilities of a package version use package_risk. First call each day returns the data itself, free; later calls return the paid request.

    Annotations the server declares

    • title: Vuln cve
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • vuln_kev_newUse when you track exploited vulnerabilities: CVEs CISA added to its Known Exploited Vulnerabilities catalog since a date (since=YYYY-MM-DD), newest first, with date added, due dat…Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use when you track exploited vulnerabilities: CVEs CISA added to its Known Exploited Vulnerabilities catalog since a date (since=YYYY-MM-DD), newest first, with date added, due date, vendor, product. Returns the paid x402 request for your input (GET /vuln/kev/new, $0.003 per call; schema linked). Call that URL with an x402 or MPP client to get the data. Bad input is refused before any charge. KEV additions since a date, newest first (limit up to 200), not a lookup; for CVSS, EPSS and KEV status of one CVE use vuln_cve. First call each day returns the data itself, free; later calls return the paid request.

    Annotations the server declares

    • title: Vuln kev new
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • site_snapshotUse when you need a health and content snapshot of your own website: HTTP status, final URL, TLS, server, robots.txt and sitemap, plus WordPress REST.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "site_snapshot" says "snapshot": 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 "website": 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
    Use when you need a health and content snapshot of your own website: HTTP status, final URL, TLS, server, robots.txt and sitemap, plus WordPress REST. Returns the paid x402 request for your input (GET /site/snapshot, $0.005 per call; schema linked). Call that URL with an x402 or MPP client to get the data. Bad input is refused before any charge. For DNS, SPF, DMARC and registration use domain_report; to check a site together with an IP, CVE or package use check_infra. First call each day returns the data itself, free; later calls return the paid request.

    Annotations the server declares

    • title: Site snapshot
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • 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.

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 write9
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
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.

Tools listed without sign-in

Looked at Nov 21, 2026, 19:22 UTC, unchanged since Nov 7, 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
8
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://x402-bazaar-rank.x402-bazaar-rank-worker.workers.dev/.well-known/oauth-protected-resource
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 8 tools that change things (8 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://x402-bazaar-rank.x402-bazaar-rank-worker.workers.dev/mcp/cve-package-domain-security: tools/list returned 9 tools to an anonymous client, including vuln_cve (write), vuln_kev_new (write), package_risk (write), software_eol (write), domain_report (write) and 3 more

    What this check looks for

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.

  1. Tools9 changed.~9 changedView diff
  2. Tools9 changed.~9 changedView diff

Install

Pinned to version 1.0.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http cve-package-domain-security https://x402-bazaar-rank.x402-bazaar-rank-worker.workers.dev/mcp/cve-package-domain-security
claude mcp add --transport http cve-package-domain-security https://x402-bazaar-rank.x402-bazaar-rank-worker.workers.dev/mcp/cve-package-domain-security

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__cve-package-domain-security__vuln_cve",
      "mcp__cve-package-domain-security__vuln_kev_new",
      "mcp__cve-package-domain-security__package_risk",
      "mcp__cve-package-domain-security__software_eol",
      "mcp__cve-package-domain-security__domain_report",
      "mcp__cve-package-domain-security__domain_report_batch",
      "mcp__cve-package-domain-security__ip_passport",
      "mcp__cve-package-domain-security__check_infra",
      "mcp__cve-package-domain-security__site_snapshot"
    ],
    "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 cve-package-domain-security. Review it before you use it.

Capability tags behind 9 rules
  • mcp__cve-package-domain-security__vuln_cve untrusted-input
  • mcp__cve-package-domain-security__vuln_kev_new untrusted-input
  • mcp__cve-package-domain-security__package_risk untrusted-input
  • mcp__cve-package-domain-security__software_eol untrusted-input
  • mcp__cve-package-domain-security__domain_report untrusted-input
  • mcp__cve-package-domain-security__domain_report_batch untrusted-input
  • mcp__cve-package-domain-security__ip_passport untrusted-input
  • mcp__cve-package-domain-security__check_infra untrusted-input
  • mcp__cve-package-domain-security__site_snapshot 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.workers.x402-bazaar-rank-worker.x402-bazaar-rank/cve-package-domain-security/verify?hash=24f443243c46042b3fc198f639034981312269e9069f484634490ee58270efcc" | jq -e '.changed == false'

Pinned hash 24f443243c46, from Nov 13, 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.workers.x402-bazaar-rank-worker.x402-bazaar-rank/cve-package-domain-security/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for dev.workers.x402-bazaar-rank-worker.x402-bazaar-rank/cve-package-domain-security
[![Anlyon Radar](https://radar.anlyon.com/badge/dev.workers.x402-bazaar-rank-worker.x402-bazaar-rank/cve-package-domain-security.svg)](https://radar.anlyon.com/servers/dev.workers.x402-bazaar-rank-worker.x402-bazaar-rank/cve-package-domain-security)

Source: MCP Registry. Synced Nov 13, 2026, 14:17 UTC.

P0: CVE, package and domain checks MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the P0: CVE, package and domain checks MCP server safe?

No scan can promise that. What its definitions show: 9 tools, 8 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 P0: CVE, package and domain checks MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the P0: CVE, package and domain checks 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 P0: CVE, package and domain checks MCP server have?

9 tools: 8 write, 1 read. vuln_cve, vuln_kev_new, package_risk, software_eol, domain_report, domain_report_batch, ip_passport, check_infra and 1 more.

Does the P0: CVE, package and domain checks MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the P0: CVE, package and domain checks MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): site_snapshot.

Has the P0: CVE, package and domain checks MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 13, 2026. Every change is on this page and in its Atom feed.