Skip to content

Nalvorn Checks MCP server

io.github.Kerio-byte/nalvorn-checksKerio-bytestreamable-httpv1.0.0Scanned

Deterministic agent checks: manifests, schemas, receipts, OpenAPI drift, DNS, TLS, headers.

12 tools: 1 do something that can't be undone, 9 change things and 2 only read.

Tools: 0 delete, 1 irreversible, 9 write, 2 read.
  • Reads private data · 1
  • Reads text others write · 12
  • Can send data out · 3
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • 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 Nalvorn Checks MCP server can do

The Nalvorn Checks MCP server is published by the GitHub account Kerio-byte. It has 12 tools. It can do things that cannot be undone, such as sending, paying or publishing (payment_verdict) and create or change data (9 tools: ru_text_normalize, receipt_verify, openapi_conformance, full_report and 5 more), but cannot delete data. 2 tools only read.

1 tool reads private data (verify_manifest); 12 tools bring in text other people can write (verify_manifest, json_schema_strict, ru_text_normalize and 9 more); 3 tools can send data out of your system (full_report, http_headers and site_ready). 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.

Last scanned Nov 16, 2026, version 1.0.0.

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.

12 tools

Can't be undone 1Claude Code: ask
  • payment_verdictVerdict on a Base payment: paid, underpaid, wrong recipient, pending or reverted, with chain facts and a signed receipt Costs 0.01 USDC per call on Base (x402).Reads text others write1 finding

    Why it is in this group

    • The name "payment_verdict" says "payment": a word that usually means money moves, which cannot be taken back.
    • 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.

    Findings

    • Warn

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

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "payment_verdict" says "payment": a word that usually means money moves, which cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    Verdict on a Base payment: paid, underpaid, wrong recipient, pending or reverted, with chain facts and a signed receipt Costs 0.01 USDC per call on Base (x402). Call it over HTTP with a PAYMENT-SIGNATURE header to actually run it.

    Annotations the server declares

    • title: payment verdict
    • readOnlyHint: true
    • openWorldHint: true
Changes things 9Claude Code: ask
  • domain_postureMail and DNS posture: A/AAAA, MX, SPF, DMARC policy, CAA, with a verdict Costs 0.005 USDC per call on Base (x402).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
    Mail and DNS posture: A/AAAA, MX, SPF, DMARC policy, CAA, with a verdict Costs 0.005 USDC per call on Base (x402). Call it over HTTP with a PAYMENT-SIGNATURE header to actually run it.

    Annotations the server declares

    • title: domain posture
    • readOnlyHint: true
    • openWorldHint: true
  • full_reportOne signed report: domain and mail, certificate, headers, crawl readiness, optional package Costs 0.01 USDC per call on Base (x402).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.
    • 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.
    • untrusted-inputThe description's first sentence says "crawl": 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.
    Description, as the server wrote it
    One signed report: domain and mail, certificate, headers, crawl readiness, optional package Costs 0.01 USDC per call on Base (x402). Call it over HTTP with a PAYMENT-SIGNATURE header to actually run it.

    Annotations the server declares

    • title: full report
    • readOnlyHint: true
    • openWorldHint: true
  • http_headersSecurity headers and the redirect chain, with what is missing and why it matters Costs 0.003 USDC per call on Base (x402).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.
    • 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.
    Description, as the server wrote it
    Security headers and the redirect chain, with what is missing and why it matters Costs 0.003 USDC per call on Base (x402). Call it over HTTP with a PAYMENT-SIGNATURE header to actually run it.

    Annotations the server declares

    • title: http headers
    • readOnlyHint: true
    • openWorldHint: true
  • openapi_conformanceCheck a live API against its OpenAPI document and list mismatches Costs 0.05 USDC per call on Base (x402).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
    Check a live API against its OpenAPI document and list mismatches Costs 0.05 USDC per call on Base (x402). Call it over HTTP with a PAYMENT-SIGNATURE header to actually run it.

    Annotations the server declares

    • title: openapi conformance
    • readOnlyHint: true
    • openWorldHint: true
  • package_checkRegistry check for npm or PyPI: latest version, deprecation, licence, staleness Costs 0.002 USDC per call on Base (x402).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
    Registry check for npm or PyPI: latest version, deprecation, licence, staleness Costs 0.002 USDC per call on Base (x402). Call it over HTTP with a PAYMENT-SIGNATURE header to actually run it.

    Annotations the server declares

    • title: package check
    • readOnlyHint: true
    • openWorldHint: true
  • receipt_verifyVerify a receipt: canonical JSON digest and declared sha256 Costs 0.01 USDC per call on Base (x402).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
    Verify a receipt: canonical JSON digest and declared sha256 Costs 0.01 USDC per call on Base (x402). Call it over HTTP with a PAYMENT-SIGNATURE header to actually run it.

    Annotations the server declares

    • title: receipt verify
    • readOnlyHint: true
    • openWorldHint: true
  • ru_text_normalizeNormalise Russian text (yo, quotes, dashes, spaces) and return metrics Free of charge.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
    Normalise Russian text (yo, quotes, dashes, spaces) and return metrics Free of charge.

    Annotations the server declares

    • title: ru text normalize
    • readOnlyHint: true
    • openWorldHint: true
  • site_readyCrawl and AI readiness: robots, sitemap, llms.txt, AI-crawler blocks, response time Costs 0.005 USDC per call on Base (x402).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.
    • 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.
    • untrusted-inputThe description's first sentence says "crawl": 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.
    Description, as the server wrote it
    Crawl and AI readiness: robots, sitemap, llms.txt, AI-crawler blocks, response time Costs 0.005 USDC per call on Base (x402). Call it over HTTP with a PAYMENT-SIGNATURE header to actually run it.

    Annotations the server declares

    • title: site ready
    • readOnlyHint: true
    • openWorldHint: true
  • tls_certCertificate expiry, issuer and SAN coverage for a host, days left and verdict Costs 0.001 USDC per call on Base (x402).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
    Certificate expiry, issuer and SAN coverage for a host, days left and verdict Costs 0.001 USDC per call on Base (x402). Call it over HTTP with a PAYMENT-SIGNATURE header to actually run it.

    Annotations the server declares

    • title: tls cert
    • readOnlyHint: true
    • openWorldHint: true
Only reads 2Show 2 read-only tools
  • json_schema_strictValidate JSON against a schema; returns exact error paths Free of charge.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "validate": 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
    Validate JSON against a schema; returns exact error paths Free of charge.

    Annotations the server declares

    • title: json schema strict
    • readOnlyHint: true
    • openWorldHint: true
  • verify_manifestCompare a list of files with a sha256 manifest and report every mismatch Free of charge.Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "compare" and "file": it reads files.
    • private-dataThe input names a file (input.files), and the tool reads: it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Compare a list of files with a sha256 manifest and report every mismatch Free of charge.

    Annotations the server declares

    • title: verify manifest
    • 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.

36 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 write12
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
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__nalvorn-checks__verify_manifest"
    ]
  }
}

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 16, 2026, 14:19 UTC, unchanged since Nov 16, 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
10
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
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 10 tools that change things (1 irreversible, 9 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://tools.nalvorn.top/mcp: tools/list returned 12 tools to an anonymous client, including payment_verdict (irreversible), ru_text_normalize (write), receipt_verify (write), openapi_conformance (write), full_report (write) and 5 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "payment_verdict" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "payment_verdict" says "payment": a word that usually means money moves, which cannot be taken back.

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

claude mcp add --transport http nalvorn-checks https://tools.nalvorn.top/mcp
claude mcp add --transport http nalvorn-checks https://tools.nalvorn.top/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__nalvorn-checks__verify_manifest",
      "mcp__nalvorn-checks__json_schema_strict"
    ],
    "ask": [
      "mcp__nalvorn-checks__ru_text_normalize",
      "mcp__nalvorn-checks__payment_verdict",
      "mcp__nalvorn-checks__receipt_verify",
      "mcp__nalvorn-checks__openapi_conformance",
      "mcp__nalvorn-checks__full_report",
      "mcp__nalvorn-checks__domain_posture",
      "mcp__nalvorn-checks__tls_cert",
      "mcp__nalvorn-checks__http_headers",
      "mcp__nalvorn-checks__package_check",
      "mcp__nalvorn-checks__site_ready"
    ],
    "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 nalvorn-checks. Review it before you use it.

Capability tags behind 12 rules
  • mcp__nalvorn-checks__verify_manifest private-data, untrusted-input
  • mcp__nalvorn-checks__json_schema_strict untrusted-input
  • mcp__nalvorn-checks__ru_text_normalize untrusted-input
  • mcp__nalvorn-checks__payment_verdict untrusted-input
  • mcp__nalvorn-checks__receipt_verify untrusted-input
  • mcp__nalvorn-checks__openapi_conformance untrusted-input
  • mcp__nalvorn-checks__full_report untrusted-input, outbound
  • mcp__nalvorn-checks__domain_posture untrusted-input
  • mcp__nalvorn-checks__tls_cert untrusted-input
  • mcp__nalvorn-checks__http_headers untrusted-input, outbound
  • mcp__nalvorn-checks__package_check untrusted-input
  • mcp__nalvorn-checks__site_ready 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.Kerio-byte/nalvorn-checks/verify?hash=76c4efe1e83b711258bef0459f64093020dbfe2c6f1b5122296bd0c93cca7a80" | jq -e '.changed == false'

Pinned hash 76c4efe1e83b, from Nov 16, 2026, 09:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.Kerio-byte/nalvorn-checks/changes.xml

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

Badge

Anlyon Radar badge for io.github.Kerio-byte/nalvorn-checks
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.Kerio-byte/nalvorn-checks.svg)](https://radar.anlyon.com/servers/io.github.Kerio-byte/nalvorn-checks)

Source: MCP Registry. Synced Nov 16, 2026, 09:17 UTC.

Nalvorn Checks MCP server: questions and answers

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

Is the Nalvorn Checks MCP server safe?

No scan can promise that. What its definitions show: 12 tools, 10 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 Nalvorn 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 Nalvorn Checks MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: payment_verdict.

What tools does the Nalvorn Checks MCP server have?

12 tools: 1 irreversible, 9 write, 2 read. payment_verdict, ru_text_normalize, receipt_verify, openapi_conformance, full_report, domain_posture, tls_cert, http_headers and 4 more.

Does the Nalvorn Checks MCP server need sign-in or OAuth?

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

Does the Nalvorn Checks MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): full_report, http_headers and site_ready.

Has the Nalvorn Checks MCP server changed its tools?

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