Skip to content

Stackhal MCP server

io.github.bahdanhal/stackhalbahdanhalstreamable-httpv1.2.0Scanned

Outside-in DNS, email security, SEO, GEO and app-link checks plus developer utilities.

13 tools: 6 change things and 7 only read.

Tools: 0 delete, 0 irreversible, 6 write, 7 read.
  • Reads private data · 2
  • Reads text others write · 6
  • Can send data out · 2
  • 5 findings

Tools listed without sign-in. Remote posture

With Anlyon

6 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 Stackhal MCP server can do

The Stackhal MCP server is published by the GitHub account bahdanhal. It has 13 tools. It can create or change data (6 tools: audit_website_seo, transpile_to_caddyfile, generate_favicon_suite, generate_apple_pkpass_spec and 2 more), but cannot delete data. 7 tools only read.

2 tools read private data (diagnose_cors_policy and inspect_domain_security); 6 tools bring in text other people can write (validate_app_links, audit_website_seo, diagnose_cors_policy and 3 more); 2 tools can send data out of your system (audit_website_seo and analyze_geo_readiness). 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 5 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 16, 2026, version 1.2.0.

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.

13 tools

Changes things 6Claude Code: ask
  • audit_website_seoRun a deterministic technical SEO audit for a public website URL.Reads text others writeCan send data out1 finding

    Why it is in this group

    • The description's first verb is "run": a word for a change.
    • 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.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Findings

    • Warn

      The server marks "audit_website_seo" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Run a deterministic technical SEO audit for a public website URL. Checks canonicals, title tags, headings, robots.txt, sitemaps, redirects, crawl traps, and indexability.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • generate_apple_pkpass_specGenerate a production-ready, fully compliant Apple Wallet pass.json specification based on pass type, metadata, colors, barcode, and field values.1 finding

    Why it is in this group

    • The name "generate_apple_pkpass_spec" says "generate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "generate_apple_pkpass_spec" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "generate_apple_pkpass_spec" says "generate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Generate a production-ready, fully compliant Apple Wallet pass.json specification based on pass type, metadata, colors, barcode, and field values.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • generate_favicon_suiteGenerate modern multi-platform favicon bundle (adaptive dark-mode SVG, multi-resolution ICO, Apple Touch Icon, Android PWA icons, webmanifest) and minimal HTML tags from SVG or ima…1 finding

    Why it is in this group

    • The name "generate_favicon_suite" says "generate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "generate_favicon_suite" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "generate_favicon_suite" says "generate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Generate modern multi-platform favicon bundle (adaptive dark-mode SVG, multi-resolution ICO, Apple Touch Icon, Android PWA icons, webmanifest) and minimal HTML tags from SVG or image input.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • repair_apple_pkpass_specAutomatically repair and sanitize broken Apple Wallet pass.json manifests: fixes missing formatVersion, prefixes passTypeIdentifier, ensures 10-character team ID, normalizes dates …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
    Automatically repair and sanitize broken Apple Wallet pass.json manifests: fixes missing formatVersion, prefixes passTypeIdentifier, ensures 10-character team ID, normalizes dates to ISO 8601 with timezones, and auto-corrects low contrast.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • transpile_regex_engineTranspile and analyze regular expressions across engines (PCRE, Go RE2, JavaScript, Python re, Rust regex) with compatibility checks and ReDoS safety analysis.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
    Transpile and analyze regular expressions across engines (PCRE, Go RE2, JavaScript, Python re, Rust regex) with compatibility checks and ReDoS safety analysis.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • transpile_to_caddyfileTranspile Nginx (nginx.conf, server blocks) or Apache (.htaccess, VirtualHost) web server configuration to clean, idiomatic Caddyfile with migration advisories.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
    Transpile Nginx (nginx.conf, server blocks) or Apache (.htaccess, VirtualHost) web server configuration to clean, idiomatic Caddyfile with migration advisories.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
Only reads 7Show 7 read-only tools
  • analyze_geo_readinessAnalyze Generative Engine Optimization (GEO) signals and AI crawler readiness for a web page (schema, citations, provenance, answer structure, llms.txt, AI bot robots rules).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "analyze_geo_readiness" says "analyze": 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 "analyze" 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
    Analyze Generative Engine Optimization (GEO) signals and AI crawler readiness for a web page (schema, citations, provenance, answer structure, llms.txt, AI bot robots rules).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • calculate_cidr_overlapAnalyze IPv4/IPv6 CIDR subnets for range collisions, full containment, 2D bit-tree matrix partition, and available free subnet allocation.No findings

    Why it is in this group

    • The description's first verb is "analyze": a word for reading.
    Description, as the server wrote it
    Analyze IPv4/IPv6 CIDR subnets for range collisions, full containment, 2D bit-tree matrix partition, and available free subnet allocation.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • diagnose_cors_policyAnalyze CORS HTTP request and response headers for wildcard/credential security violations, missing Vary: Origin, preflight OPTIONS handling, and header exposure.Reads private dataReads text others write2 findings

    Why it is in this group

    • The description's first verb is "analyze": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "analyze" and "credential": it reads secrets.
    • untrusted-inputThe description's first sentence says "analyze" and "http": it reads web pages, which anyone can write.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...quest and response headers for wildcard/credential security violations, missing Vary: Orig..."

      What this check looks for
    • Info

      The input schema at properties.with_credentials.description mentions "credentials".

      Matched text

      inputSchema.properties.with_credentials.description: "...quest includes cookies or authorization credentials."

      What this check looks for
    Description, as the server wrote it
    Analyze CORS HTTP request and response headers for wildcard/credential security violations, missing Vary: Origin, preflight OPTIONS handling, and header exposure.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • inspect_apple_pkpassInspect and validate Apple Wallet .pkpass JSON structure (pass.json) or package manifests: checks required keys, pass styles, dates, ISO 8601 timezones, transit types, barcodes, an…No findings

    Why it is in this group

    • The name "inspect_apple_pkpass" says "inspect": a word for reading.
    Description, as the server wrote it
    Inspect and validate Apple Wallet .pkpass JSON structure (pass.json) or package manifests: checks required keys, pass styles, dates, ISO 8601 timezones, transit types, barcodes, and color contrast.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • inspect_domain_securityInspect domain email security and deliverability standards: DMARC (BIMI compliance), BIMI DNS & SVG reachability, MTA-STS (RFC 8461), SMTP TLS-RPT (RFC 8460), SPF and MX records.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "inspect_domain_security" says "inspect": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "inspect" and "email": it reads mail.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "inspect" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Inspect domain email security and deliverability standards: DMARC (BIMI compliance), BIMI DNS & SVG reachability, MTA-STS (RFC 8461), SMTP TLS-RPT (RFC 8460), SPF and MX records.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • trace_dns_delegationQuery live DNS records and inspect the authoritative nameservers returned for a domain.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "query": a word for reading.

    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
    Query live DNS records and inspect the authoritative nameservers returned for a domain.

    Annotations the server declares

    • readOnlyHint: 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.

24 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 write6
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__stackhal__analyze_geo_readiness",
      "mcp__stackhal__audit_website_seo"
    ]
  }
}

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 20, 2026, 19:02 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
6
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 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://stackhal.com/mcp: tools/list returned 13 tools to an anonymous client, including audit_website_seo (write), transpile_to_caddyfile (write), generate_favicon_suite (write), generate_apple_pkpass_spec (write), repair_apple_pkpass_spec (write) and 1 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

3 warn2 info
  • The server marks "audit_website_seo" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.

    What this check looks for
  • The server marks "generate_favicon_suite" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "generate_favicon_suite" says "generate": a word for a change.

    What this check looks for
  • The server marks "generate_apple_pkpass_spec" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "generate_apple_pkpass_spec" says "generate": a word for a change.

    What this check looks for
  • The description mentions "credential".

    Matched text

    description: "...quest and response headers for wildcard/credential security violations, missing Vary: Orig..."

    What this check looks for
  • The input schema at properties.with_credentials.description mentions "credentials".

    Matched text

    inputSchema.properties.with_credentials.description: "...quest includes cookies or authorization credentials."

    What this check looks for

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 1.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http stackhal https://stackhal.com/mcp
claude mcp add --transport http stackhal https://stackhal.com/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__stackhal__validate_app_links",
      "mcp__stackhal__calculate_cidr_overlap",
      "mcp__stackhal__diagnose_cors_policy",
      "mcp__stackhal__trace_dns_delegation",
      "mcp__stackhal__inspect_domain_security",
      "mcp__stackhal__inspect_apple_pkpass"
    ],
    "ask": [
      "mcp__stackhal__audit_website_seo",
      "mcp__stackhal__transpile_to_caddyfile",
      "mcp__stackhal__generate_favicon_suite",
      "mcp__stackhal__analyze_geo_readiness",
      "mcp__stackhal__generate_apple_pkpass_spec",
      "mcp__stackhal__repair_apple_pkpass_spec",
      "mcp__stackhal__transpile_regex_engine"
    ],
    "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 stackhal. Review it before you use it.

Capability tags behind 6 rules
  • mcp__stackhal__validate_app_links untrusted-input
  • mcp__stackhal__audit_website_seo untrusted-input, outbound
  • mcp__stackhal__diagnose_cors_policy private-data, untrusted-input
  • mcp__stackhal__trace_dns_delegation untrusted-input
  • mcp__stackhal__inspect_domain_security private-data, untrusted-input
  • mcp__stackhal__analyze_geo_readiness 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/io.github.bahdanhal/stackhal/verify?hash=c99742f568d2de098872fd53839bcf83d08010dfdf62ba6b4cba3478dcba60ce" | jq -e '.changed == false'

Pinned hash c99742f568d2, from Nov 16, 2026, 10:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.bahdanhal/stackhal/changes.xml

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

Badge

Anlyon Radar badge for io.github.bahdanhal/stackhal
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.bahdanhal/stackhal.svg)](https://radar.anlyon.com/servers/io.github.bahdanhal/stackhal)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:23 UTC.

Stackhal MCP server: questions and answers

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

Is the Stackhal MCP server safe?

No scan can promise that. What its definitions show: 13 tools, 6 of which can change, send or delete something, and 5 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 Stackhal MCP server delete data?

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

Can the Stackhal 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 Stackhal MCP server have?

13 tools: 6 write, 7 read. audit_website_seo, transpile_to_caddyfile, generate_favicon_suite, generate_apple_pkpass_spec, repair_apple_pkpass_spec, transpile_regex_engine, validate_app_links, calculate_cidr_overlap and 5 more.

Does the Stackhal MCP server need sign-in or OAuth?

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

Does the Stackhal 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): audit_website_seo and analyze_geo_readiness.

Has the Stackhal MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.