Skip to content

OrionCMD Checks MCP server

com.orioncmd.api/checksapi.orioncmd.comstreamable-httpv1.5.0Scanned

Domain threat checks, a 30-day domain watch, TLS/DNS/email-auth checks and a $2 site audit (x402).

14 tools: 12 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 12 write, 2 read.
  • Reads private data · 1
  • Reads text others write · 11
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

12 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 OrionCMD Checks MCP server can do

The OrionCMD Checks MCP server is published by api.orioncmd.com, a domain the MCP Registry verified. It has 14 tools. It can create or change data (12 tools: pricing, check_cert, check_dns, check_domain_expiry and 8 more), but cannot delete data. 2 tools only read.

1 tool reads private data (watch_status); 11 tools bring in text other people can write (check_cert, check_dns, check_domain_expiry and 8 more).

The fixed checks matched 2 findings (credentials-mention and 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 13, 2026, version 1.5.0.

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.

14 tools

Changes things 12Claude Code: ask
  • bulk_threat_checkCheck up to 100 domains or IPv4 addresses at once against ThreatCluster's high-confidence 30-day IOC feed; each domain is resolved and its IPv4 matched too.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 up to 100 domains or IPv4 addresses at once against ThreatCluster's high-confidence 30-day IOC feed; each domain is resolved and its IPv4 matched too. IOC only (no ransomware-claim lookups; use threat_check for one domain). Stale feed returns an error and is not charged. Costs $0.50 USDC per call via x402 (payment goes in _meta["x402/payment"]); invalid input or an upstream failure returns an error and is not charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • idempotentHint: true
  • check_certCheck the TLS certificate of one hostname: issuer, validity dates, days left, % of lifetime used, renewal cadence and a renewal-stall flag, plus a live HTTPS pass/fail probe.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 the TLS certificate of one hostname: issuer, validity dates, days left, % of lifetime used, renewal cadence and a renewal-stall flag, plus a live HTTPS pass/fail probe. Use it when you only need certificate health; use site_health for cert + DNS + expiry together, or domain_grade for a scored A-F result. Certificate details come from public Certificate Transparency logs (Cert Spotter, crt.sh fallback), not from the live connection, so a brand-new cert may not show yet. Read-only; makes one HTTPS request to the host and one CT-log query, usually 1-5 s. Costs $0.01 USDC per call via x402 (payment goes in _meta["x402/payment"]); invalid input or an upstream failure returns an error and is not charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • idempotentHint: true
  • check_dnsLook up the live DNS of a domain: NS, A/AAAA/CNAME, MX, SPF, DMARC, CAA (climbing to the parent zone) and DNSSEC status, with plain-English findings.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
    Look up the live DNS of a domain: NS, A/AAAA/CNAME, MX, SPF, DMARC, CAA (climbing to the parent zone) and DNSSEC status, with plain-English findings. Use it for a DNS inventory or to debug resolution; use check_email_auth for a deeper SPF/DMARC/DKIM/MTA-STS review. Queries Cloudflare DNS-over-HTTPS (1.1.1.1) at call time; read-only, nothing is stored. Costs $0.01 USDC per call via x402 (payment goes in _meta["x402/payment"]); invalid input or an upstream failure returns an error and is not charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • idempotentHint: true
  • check_domain_expiryCheck when a domain registration expires: registrar, registered and expiry dates, days left, EPP status codes and nameservers, from the registry's RDAP server.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 when a domain registration expires: registrar, registered and expiry dates, days left, EPP status codes and nameservers, from the registry's RDAP server. Use it for renewal risk on the registered domain (not the certificate; use check_cert for that). Some TLDs publish no RDAP service, in which case found=false explains why. Read-only. Costs $0.01 USDC per call via x402 (payment goes in _meta["x402/payment"]); invalid input or an upstream failure returns an error and is not charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • idempotentHint: true
  • check_email_authReview the email authentication setup of a domain: SPF validity and DNS-lookup count (limit 10), DMARC policy, pct and reporting, DKIM on common selector names, MTA-STS mode, TLS-R…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
    Review the email authentication setup of a domain: SPF validity and DNS-lookup count (limit 10), DMARC policy, pct and reporting, DKIM on common selector names, MTA-STS mode, TLS-RPT and BIMI, with a rough 0-100 score and plain-English fixes. Use it before sending mail from a domain or when mail lands in spam. DKIM is only checked on common selectors, so "not found" is not proof DKIM is missing. Live DNS via Cloudflare DoH; read-only, no email is sent. Costs $0.01 USDC per call via x402 (payment goes in _meta["x402/payment"]); invalid input or an upstream failure returns an error and is not charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • idempotentHint: true
  • check_security_headersCheck the HTTP security headers of a website with one live HTTPS GET: redirect chain (up to 5 hops), final status, HSTS, CSP, X-Frame-Options, X-Content-Type-Options, Referrer-Poli…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 the HTTP security headers of a website with one live HTTPS GET: redirect chain (up to 5 hops), final status, HSTS, CSP, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, Permissions-Policy and COOP, with a simple A-F header grade and findings. Use it for web-hardening checks; it is not a vulnerability scan. The page body is not read or stored. Costs $0.01 USDC per call via x402 (payment goes in _meta["x402/payment"]); invalid input or an upstream failure returns an error and is not charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • idempotentHint: true
  • domain_gradeGrade a domain's security posture A-F in one call, for vendor-risk or due-diligence checks.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
    Grade a domain's security posture A-F in one call, for vendor-risk or due-diligence checks. Runs the TLS, DNS (DNSSEC, CAA), registration-expiry, email-auth and HTTP-header checks and returns one letter, a 0-100 score, points per category (TLS 25, email 25, headers 20, DNS 15, registration 15) and the top fixes. Use it when you want a verdict; use site_health or the single checks when you need raw data. Unavailable categories are left out of the percentage (partial=true). Read-only; takes about 3-10 s. Costs $0.03 USDC per call via x402 (payment goes in _meta["x402/payment"]); invalid input or an upstream failure returns an error and is not charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • idempotentHint: true
  • expiry_batchCertificate and domain-registration expiry for 2 to 5 domains in one call: days left, expiry dates and an ok/warn/expired status per domain, plus the soonest date overall.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 and domain-registration expiry for 2 to 5 domains in one call: days left, expiry dates and an ok/warn/expired status per domain, plus the soonest date overall. Certificate dates come from CT logs, registration dates from RDAP. Partial results if some lookups fail; if every domain fails it returns an error and is not charged. Costs $0.04 USDC per call via x402 (payment goes in _meta["x402/payment"]); invalid input or an upstream failure returns an error and is not charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • idempotentHint: true
  • full_site_auditFull site audit report for one domain, for client reports, vendor reviews or a pre-launch check.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
    Full site audit report for one domain, for client reports, vendor reviews or a pre-launch check. Runs every check (TLS from CT logs + live probe, DNS/DNSSEC/CAA, registration expiry and transfer lock, SPF/DMARC/DKIM/MTA-STS, security headers) plus HTTP->HTTPS redirect, www/apex consistency, RFC 9116 security.txt, robots.txt and sitemap. Returns the A-F grade and score (same weights as domain_grade), an action plan sorted critical > high > medium > low where each item has the exact fix and effort, and every raw section. Use domain_grade for just the letter. Fails (not charged) if 3+ core checks fail. Read-only; about 5-15 s. Costs $2 USDC per call via x402 (payment goes in _meta["x402/payment"]); invalid input or an upstream failure returns an error and is not charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • idempotentHint: true
  • pricingFree.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
    Free. Return the price of every paid tool, the payment network (Base) and the receiving address, so you can budget before calling. No input, no network request, no payment.

    Annotations the server declares

    • title: Prices (free)
    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
    • destructiveHint: false
  • site_healthRun check_cert, check_dns and check_domain_expiry together and return their raw results plus a short summary, the renewal-stall flag and the Let's Encrypt 64-day certificate note (…Reads text others write1 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.

    Findings

    • Warn

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

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":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 check_cert, check_dns and check_domain_expiry together and return their raw results plus a short summary, the renewal-stall flag and the Let's Encrypt 64-day certificate note (from 2027-02-10). Use it for a full data dump in one call; use domain_grade if you want a single scored A-F answer that also covers email auth and HTTP headers. If one or two sources fail you get partial=true with the rest. Read-only. Costs $0.03 USDC per call via x402 (payment goes in _meta["x402/payment"]); invalid input or an upstream failure returns an error and is not charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • idempotentHint: true
  • threat_checkIs this domain known-bad?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
    Is this domain known-bad? Resolves the hostname (A/AAAA), matches the name, its parent domains and resolved IPv4 against ThreatCluster's high-confidence 30-day IOC feed (cached, refreshed about hourly), and looks up ransomware leak-site claims naming the domain (commercially reusable sources via Dragons Eye). Returns verdict listed, claimed, listed_and_claimed or no_known_threat with the matching reports. No match is not proof of safety; claims are unverified attacker assertions. Stale feed or source failure returns an error and is not charged. Costs $0.02 USDC per call via x402 (payment goes in _meta["x402/payment"]); invalid input or an upstream failure returns an error and is not charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • destructiveHint: false
    • idempotentHint: true
Only reads 2Show 2 read-only tools
  • validate_targetFree.1 finding

    Why it is in this group

    • The name "validate_target" says "validate": a word for reading.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...esses, single-label names and URLs with credentials."

      What this check looks for
    Description, as the server wrote it
    Free. Check that a domain or URL is well-formed and get the normalized hostname, before calling a paid check. Offline: no network request, no payment. Rejects IP addresses, single-label names and URLs with credentials.

    Annotations the server declares

    • title: Validate domain (free)
    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
    • destructiveHint: false
  • watch_statusFree.Reads private dataNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe input names a secret (input.webhook_secret), and the tool reads: it reads secrets.
    Description, as the server wrote it
    Free. Status of a paid domain watch (created with HTTP POST /v1/watch): items, expiry, last check, current DNS/IOC/claim state, last webhook delivery. Needs the webhook_secret from creation.

    Annotations the server declares

    • title: Watch status (free)
    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
    • destructiveHint: 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.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write11
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
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 20, 2026, 18:44 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
12
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 12 tools that change things (12 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.orioncmd.com/mcp: tools/list returned 14 tools to an anonymous client, including pricing (write), check_cert (write), check_dns (write), check_domain_expiry (write), site_health (write) and 7 more

    What this check looks for

Posture changes

  1. Oct 29, 2026
    • Tools that change things, listed without credentials: 11 to 12

Findings

Matches of fixed checks, with the text they matched.

1 warn1 info
  • The server marks "site_health" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

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

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

    Matched text

    description: "...esses, single-label names and URLs with credentials."

    What this check looks for

History

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

  1. Tools1 added, 1 changed.+1 added~1 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 11 -> 12.View diff
    • Tools that change things, listed without credentials: 11 to 12

Install

Pinned to version 1.5.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http checks https://api.orioncmd.com/mcp
claude mcp add --transport http checks https://api.orioncmd.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__checks__validate_target",
      "mcp__checks__watch_status"
    ],
    "ask": [
      "mcp__checks__pricing",
      "mcp__checks__check_cert",
      "mcp__checks__check_dns",
      "mcp__checks__check_domain_expiry",
      "mcp__checks__site_health",
      "mcp__checks__check_email_auth",
      "mcp__checks__check_security_headers",
      "mcp__checks__domain_grade",
      "mcp__checks__full_site_audit",
      "mcp__checks__threat_check",
      "mcp__checks__bulk_threat_check",
      "mcp__checks__expiry_batch"
    ],
    "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 checks. Review it before you use it.

Capability tags behind 12 rules
  • mcp__checks__check_cert untrusted-input
  • mcp__checks__check_dns untrusted-input
  • mcp__checks__check_domain_expiry untrusted-input
  • mcp__checks__site_health untrusted-input
  • mcp__checks__check_email_auth untrusted-input
  • mcp__checks__check_security_headers untrusted-input
  • mcp__checks__domain_grade untrusted-input
  • mcp__checks__full_site_audit untrusted-input
  • mcp__checks__threat_check untrusted-input
  • mcp__checks__bulk_threat_check untrusted-input
  • mcp__checks__expiry_batch untrusted-input
  • mcp__checks__watch_status private-data

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/com.orioncmd.api/checks/verify?hash=ef6676bb238ccc559e311c0e8fe5149d04432e6d78e4b8e0486e09481fbd9b36" | jq -e '.changed == false'

Pinned hash ef6676bb238c, from Nov 13, 2026, 23:18 UTC.

Watch

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

https://radar.anlyon.com/servers/com.orioncmd.api/checks/changes.xml

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

Badge

Anlyon Radar badge for com.orioncmd.api/checks
[![Anlyon Radar](https://radar.anlyon.com/badge/com.orioncmd.api/checks.svg)](https://radar.anlyon.com/servers/com.orioncmd.api/checks)

Source: MCP Registry. Synced Oct 21, 2026, 18:00 UTC.

OrionCMD Checks MCP server: questions and answers

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

Is the OrionCMD Checks MCP server safe?

No scan can promise that. What its definitions show: 14 tools, 12 of which can change, send or delete something, and 2 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 OrionCMD 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 OrionCMD 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 OrionCMD Checks MCP server have?

14 tools: 12 write, 2 read. pricing, check_cert, check_dns, check_domain_expiry, site_health, check_email_auth, check_security_headers, domain_grade and 6 more.

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

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

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

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the OrionCMD Checks MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 1, 2026. Every change is on this page and in its Atom feed.