Skip to content

VulKill Security MCP server

io.github.dytredline/vulkill-securitydytredlinestreamable-httpv1.2.1Scanned

Autonomous AppSec & DAST scanner across 12 security domains (260+ controls) with 3-Layer Triage.

12 tools: 8 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 8 write, 4 read.
  • Reads private data · 2
  • Reads text others write · 4
  • Can send data out · 2
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

8 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.
Govern this server →

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 VulKill Security MCP server can do

The VulKill Security MCP server is published by the GitHub account dytredline. It has 12 tools. It can create or change data (8 tools: vulkill_check_credits, vulkill_credit_usage, vulkill_estimate_scan, vulkill_ai_guide and 4 more), but cannot delete data. 4 tools only read.

2 tools read private data (vulkill_wallet_status and search); 4 tools bring in text other people can write (vulkill_start_scan, vulkill_auto_scan, vulkill_get_scan_status and 1 more); 2 tools can send data out of your system (vulkill_start_scan and vulkill_auto_scan). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

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 1.2.1.

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.

12 tools

Changes things 8Claude Code: ask
  • vulkill_ai_guideYeni bağlantıda önce bu aracı kullanın: API/MCP akışını, tarama modlarını, hedef doğrulamasını ve kullanıcı yetki beyanını açıklar.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
    Yeni bağlantıda önce bu aracı kullanın: API/MCP akışını, tarama modlarını, hedef doğrulamasını ve kullanıcı yetki beyanını açıklar. Sonraki adım bakiye için vulkill_wallet_status, özellik araması için vulkill_capabilities. Tarama başlatmaz; kredi harcamaz.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • vulkill_auto_scanEski istemciler için tarama başlatma uyumluluk aracı; yeni entegrasyonlarda vulkill_start_scan tercih edin.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 server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.targetUrl): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Eski istemciler için tarama başlatma uyumluluk aracı; yeni entegrasyonlarda vulkill_start_scan tercih edin. Aynı yetki/kredi/motor kontrollerini kullanır. sourceFiles veya inline_files ile içerik; targetUrl veya tek dast_targets ile doğrulanmış HTTPS hedefi gönderilir. Yerel project_path ve depo adresi içe aktarma değildir. Her istek en fazla 5000 dosya ve toplam 512 KiB JSON içerebilir; daha büyük projeleri ayrı tarama istekleri halinde gönderin. Her grup için farklı idempotencyKey kullanın; aynı grubun yeniden denemesinde aynı anahtarı koruyun. Açık kullanıcı beyanı zorunludur ve her grubun raporu kendi scanId'si ile izlenir.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: true
  • vulkill_capabilities12 güvenlik alanını, 260 kontrolün katalog kapsamını ve 5 tarama modunu açıklar.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
    12 güvenlik alanını, 260 kontrolün katalog kapsamını ve 5 tarama modunu açıklar. Boş query özet getirir; query=all tüm 260 maddeyi; mod adı, VK-001, SQL veya CWE-89 ayrıntılı eşleşmeleri getirir. Modlar 3 yetki beyanından ayrıdır. Çalıştırılan kontroller için görev raporunu okuyun. Tarama başlatmaz, kredi harcamaz.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • vulkill_check_creditsTarama öncesi yetki kapsamlarını, beyan metnini, dosya/site kredisini ve süre sınırlarını getirir.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
    Tarama öncesi yetki kapsamlarını, beyan metnini, dosya/site kredisini ve süre sınırlarını getirir. Yalnız sayısal bakiye ve motor hazırlığı için vulkill_wallet_status, geçmiş için vulkill_credit_usage kullanın. Tarama başlatmaz; kredi harcamaz.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • vulkill_credit_usageGüncel dönemin kredi kullanımını ve en son görev özetlerini getirir.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
    Güncel dönemin kredi kullanımını ve en son görev özetlerini getirir. view uyumluluk alanıdır; historical seçimi geçmiş dönem bakiyesi sorgulamaz. Anlık bakiye için vulkill_wallet_status kullanın. Kredi harcamaz.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • vulkill_estimate_scanDosya ve site sayısından kredi kapsamı ve işçi sınıflarının tahminini oluşturur.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
    Dosya ve site sayısından kredi kapsamı ve işçi sınıflarının tahminini oluşturur. Bu yalnız tahmindir; kaynaklar gönderilmez ve görev başlamaz. 5.000 dosya üzerindeki çoklu işçi dağıtımı henüz desteklenmiyor. Kredi harcamaz.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • vulkill_get_scan_statusvulkill_start_scan sonucundaki scanId için yetkili motordan durum ve rapor günceller.Reads text others write1 finding

    Why it is in this group

    • The name "vulkill_get_scan_status" says "get": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "vulkill_get_scan_status" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "vulkill_get_scan_status" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    vulkill_start_scan sonucundaki scanId için yetkili motordan durum ve rapor günceller. Yeni tarama başlatmaz. Motor başlamadığını doğrularsa ayrılmış kredi uzlaştırılır; zaman aşımı tek başına iade kanıtı değildir. Bulunmayan kimlik not_found, başka hesaba ait kimlik forbidden döner. running ise sonra yeniden sorgulayın; completed ise findings/coverage/summary inceleyin. Büyük raporda findingsTotal toplamı ve findingsNextCursor sonraki sayfayı gösterir; tüm bulguları görmek için findingsCursor ile sayfaları sırayla isteyin.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: true
  • vulkill_start_scanYeni istemciler için birincil tarama başlatma aracı.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "vulkill_start_scan" says "start": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.targetUrl): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Yeni istemciler için birincil tarama başlatma aracı. Kaynak dosyalarını sourceFiles içinde veya sahipliği doğrulanmış HTTPS hedefini targetUrl içinde gönderin; yerel yol ve GitHub depo adresi dosya içeriğinin yerine geçmez. authorizationScope seçimi ve kullanıcının açık liabilityAccepted=true onayı gerekir; kullanıcı adına kabul etmeyin. Her istek en fazla 5000 dosya ve toplam 512 KiB JSON içerebilir; büyük projeyi her biri bu iki sınıra uyan ayrı tarama isteklerine bölün. Sonraki grup kendiliğinden gönderilmez. Her grup için farklı idempotencyKey kullanın; aynı grubu ağ hatası sonrası tekrarlarken aynı anahtarı koruyun. Her grubun raporunu ayrı scanId ile izleyin. Motor başlamadığı doğrulanırsa kredi düşmez.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: true
Only reads 4Show 4 read-only tools
  • fetchsearch veya vulkill_list_reports sonucundaki id ile hesabınıza ait kayıtlı raporu, formatlı dışa aktarımını (<scanId>:executive, <scanId>:vendor_trust, <scanId>:sarif, <scanId>:cyc…Reads text others writeNo findings

    Why it is in this group

    • The name "fetch" says "fetch": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "search" and "web": it reads web pages, which anyone can write.
    Description, as the server wrote it
    search veya vulkill_list_reports sonucundaki id ile hesabınıza ait kayıtlı raporu, formatlı dışa aktarımını (<scanId>:executive, <scanId>:vendor_trust, <scanId>:sarif, <scanId>:cyclonedx), örnek PDF rapor bilgisini (sample:ai-mcp, sample:web-network, sample:mobile-desktop) ya da cap- önekli yetenek kaydını getirir. Yeni tarama başlatmaz; kredi harcamaz. Çalışan görevin durumunu güncellemek için vulkill_get_scan_status kullanın. Bulunmayan ya da erişilemeyen kayıt hata döndürür.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • vulkill_list_reportsYalnız bağlı hesaba ait en yeni 50 görev ve ayrıntılı findings/coverage/summary raporlarını listeler.No findings

    Why it is in this group

    • The name "vulkill_list_reports" says "list": a word for reading.
    Description, as the server wrote it
    Yalnız bağlı hesaba ait en yeni 50 görev ve ayrıntılı findings/coverage/summary raporlarını listeler. Tarama başlatmaz ve yeni kredi harcamaz. Bir görevi motordan güncellemek için vulkill_get_scan_status; bilinen rapor kimliğini okumak için fetch kullanın.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • vulkill_wallet_statusHesabın remainingFiles, remainingSites, executionAvailable ve dönem bakiyesini getirir.Reads private dataNo findings

    Why it is in this group

    • The name "vulkill_wallet_status" says "status": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "file": it reads files.
    Description, as the server wrote it
    Hesabın remainingFiles, remainingSites, executionAvailable ve dönem bakiyesini getirir. Güncel bakiye için kullanın; geçmiş kullanım için vulkill_credit_usage. executionAvailable tamamlanmış tarama kanıtı değildir. Tarama başlatmaz; kredi harcamaz.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false

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.

16 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
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.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__vulkill-security__vulkill_auto_scan",
      "mcp__vulkill-security__vulkill_start_scan"
    ]
  }
}

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 18, 2026, 16:22 UTC, unchanged since Nov 4, 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://app.vulkill.com/.well-known/oauth-protected-resource/api/mcp
Authorization servers
https://app.vulkill.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • 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://app.vulkill.com/api/mcp: tools/list returned 12 tools to an anonymous client, including vulkill_check_credits (write), vulkill_credit_usage (write), vulkill_estimate_scan (write), vulkill_ai_guide (write), vulkill_capabilities (write) and 3 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "vulkill_get_scan_status" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "vulkill_get_scan_status" says "get": a word for reading.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools11 added, 1 removed, 1 changed.+11 added−1 removed~1 changedView diff

Install

Pinned to version 1.2.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http vulkill-security https://app.vulkill.com/api/mcp
claude mcp add --transport http vulkill-security https://app.vulkill.com/api/mcp

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": [
      "mcp__vulkill-security__vulkill_wallet_status",
      "mcp__vulkill-security__vulkill_list_reports",
      "mcp__vulkill-security__search",
      "mcp__vulkill-security__fetch"
    ],
    "ask": [
      "mcp__vulkill-security__vulkill_check_credits",
      "mcp__vulkill-security__vulkill_credit_usage",
      "mcp__vulkill-security__vulkill_estimate_scan",
      "mcp__vulkill-security__vulkill_ai_guide",
      "mcp__vulkill-security__vulkill_capabilities",
      "mcp__vulkill-security__vulkill_start_scan",
      "mcp__vulkill-security__vulkill_auto_scan",
      "mcp__vulkill-security__vulkill_get_scan_status"
    ],
    "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 vulkill-security. Review it before you use it.

Capability tags behind 6 rules
  • mcp__vulkill-security__vulkill_wallet_status private-data
  • mcp__vulkill-security__vulkill_start_scan untrusted-input, outbound
  • mcp__vulkill-security__vulkill_auto_scan untrusted-input, outbound
  • mcp__vulkill-security__vulkill_get_scan_status untrusted-input
  • mcp__vulkill-security__search private-data
  • mcp__vulkill-security__fetch 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.dytredline/vulkill-security/verify?hash=705a1fee12eb3d12a417b430fd34b02353ff880e4256b28dba50666e3de2c470" | jq -e '.changed == false'

Pinned hash 705a1fee12eb, from Nov 16, 2026, 21:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.dytredline/vulkill-security/changes.xml

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

Badge

Anlyon Radar badge for io.github.dytredline/vulkill-security
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.dytredline/vulkill-security.svg)](https://radar.anlyon.com/servers/io.github.dytredline/vulkill-security)

Source: MCP Registry · repository. Synced Nov 3, 2026, 10:17 UTC.

VulKill Security MCP server: questions and answers

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

Is the VulKill Security MCP server safe?

No scan can promise that. What its definitions show: 12 tools, 8 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the VulKill Security MCP server delete data?

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

Can the VulKill Security 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 VulKill Security MCP server have?

12 tools: 8 write, 4 read. vulkill_check_credits, vulkill_credit_usage, vulkill_estimate_scan, vulkill_ai_guide, vulkill_capabilities, vulkill_start_scan, vulkill_auto_scan, vulkill_get_scan_status and 4 more.

Does the VulKill Security MCP server need sign-in or OAuth?

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

Does the VulKill Security 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): vulkill_start_scan and vulkill_auto_scan.

Has the VulKill Security MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.