TamingDNS MCP server
com.tamingdns/mcptamingdns.comstreamable-httpv2.2.2Scanned
Check SPF, DKIM, DMARC, MX, MTA-STS, TLS-RPT, BIMI, DANE, DNSSEC and TXT; read headers and bounces.
19 tools: 13 change things and 6 only read.
- Reads private data · 2
- Reads text others write · 19
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
13 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.
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 TamingDNS MCP server can do
The TamingDNS MCP server is published by tamingdns.com, a domain the MCP Registry verified. It has 19 tools. It can create or change data (13 tools: check_spf, check_dkim, check_dmarc, check_tls_rpt and 9 more), but cannot delete data. 6 tools only read.
2 tools read private data (check_mx and analyze_email_headers); 19 tools bring in text other people can write (check_spf, check_dkim, discover_dkim and 16 more).
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 4 times since Anlyon Radar first saw them.
Last scanned Nov 14, 2026, version 2.2.2.
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.
19 tools
Changes things 13Claude Code: ask
check_bimiCheck default._bimi.<domain>: parses the BIMI record, validates the SVG Tiny-PS logo, inspects the VMC chain (expiry, EKU, SCT, issuer-accepted, SAN match, logotype hash), and veri…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 default._bimi.<domain>: parses the BIMI record, validates the SVG Tiny-PS logo, inspects the VMC chain (expiry, EKU, SCT, issuer-accepted, SAN match, logotype hash), and verifies the DMARC prerequisite (p=quarantine/reject at pct=100 with no sp=none — the RFC 7489 reading Gmail and Apple Mail evaluate today). DMARCbis (RFC 9989) aware: t= is parsed into analysis.dmarc.t, t=y emits TESTING_MODE (warn under p=quarantine — bis receivers read it as none; info under p=reject), and a present pct= emits DEPRECATED_TAG (removed by RFC 9989 Appendix A.6, advisory only). Returns grade (A-F), structured findings, and an `analysis` block (logo/vmc/dmarc/provider_matrix). Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: BIMI Record Checker
check_daneCheck SMTP DANE / TLSA records for a domain (RFC 7672).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 SMTP DANE / TLSA records for a domain (RFC 7672). Resolves the MX hosts (falls back to the apex when none), looks up the TLSA record at _25._tcp.<mx-host> over binary DoH, classifies each record (usage 0-3 / selector 0-1 / matching 0-2 per RFC 7671 §2.1), and confirms the answer carried the DNSSEC AD bit — DANE is meaningless without DNSSEC, so an unsigned TLSA answer is the dominant failure mode. Returns grade (A-F) with grade_reasons, a verdict (valid/valid_with_warnings/no_dnssec/not_configured/error), structured findings (DANE_NO_TLSA, DANE_TLSA_HOST_UNSIGNED, DANE_PKIX_TA_USED_WITHOUT_CHAIN, DANE_TLSA_EXACT_MATCH, DANE_PARTIAL_COVERAGE, DANE_TLSA_INVALID_USAGE/SELECTOR/MATCHING), and an `analysis` block (per-host TLSA records + DNSSEC status, the spec-compliance signals, and the MTA-STS cross-signal). DNS-only: it never opens a port-25 STARTTLS handshake, so it proves the TLSA records exist, are well-formed, and are DNSSEC-signed — never that they match the live cert (Hostinger and Cloudflare both block outbound 25). Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: DANE / TLSA Validator
check_dkimLook up a DKIM public key at <selector>._domainkey.<domain> and validate it.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 a DKIM public key at <selector>._domainkey.<domain> and validate it. Detects key revocation (empty p=), RSA key length (KEY_TOO_SHORT below 1024, KEY_WEAK below 2048), SHA-1 hash deprecation, and t=y test mode. For selector1/selector2 it also checks a Microsoft 365 CNAME target carries the token Microsoft builds for the domain (M365_DKIM_CNAME_MISMATCH), even when no key resolves. Returns an `analysis` block with the per-key facts (key_type, key_bits, key_strength, revoked, test_mode, hash_algs, m365_cname). Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: DKIM Checker
check_dmarcCheck the _dmarc record for a domain with DUAL discovery: the RFC 7489 §6.6.3 organisational-domain ladder (what major receivers enforce today — grade/verdict anchor to it) AND the…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 _dmarc record for a domain with DUAL discovery: the RFC 7489 §6.6.3 organisational-domain ladder (what major receivers enforce today — grade/verdict anchor to it) AND the RFC 9989 §4.10 DNS Tree Walk (8-query cap, psd=n/y stop rules, fewest-labels org selection) into analysis.discovery {legacy, tree_walk, diverges}. When the two methods select different policy records or org domains, DISCOVERY_DIVERGENCE (warn) fires with a one-notch grade downgrade. Also DMARCbis tag-aware: t=/np=/psd= parsed into analysis.tags, removed tags (pct/rf/ri) emit DEPRECATED_TAG, t=y emits TESTING_MODE with a one-notch downgrade. Returns the grade (A-F) with grade_reasons, a verdict (enforced/partial/monitoring/monitoring_blind/invalid/not_configured), structured findings (NO_DMARC_RECORD, DMARC_RECORD_IGNORED, MULTIPLE_DMARC_RECORDS, INVALID_TAG, POLICY_NONE, POLICY_NONE_NO_RUA, PCT_BELOW_100, RUA_MISSING_UNDER_ENFORCEMENT, SP_NOT_ENFORCED, EXTERNAL_RUA_UNAUTHORIZED, DMARC_INHERITED_FROM_ORG, TESTING_MODE, DEPRECATED_TAG, DISCOVERY_DIVERGENCE), and an `analysis` block with the lookup ladder, discovery, source (self/org), org_domain, normalised tags, per-recipient RUA/RUF external-authorisation detail (RFC 7489 §7.1), and rua_unauthorised. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: DMARC Record Analyser
check_dns_propagationAsk 14 public DoH resolvers in North and South America, Europe and Asia (Google, Cloudflare, Quad9, CIRA, Comcast, Mullvad, DNSPod, IIJ, DNS.SB and more) for one record type at one…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 Ask 14 public DoH resolvers in North and South America, Europe and Asia (Google, Cloudflare, Quad9, CIRA, Comcast, Mullvad, DNSPod, IIJ, DNS.SB and more) for one record type at one name, and report whether they agree. Use it after changing a record to see whether the change has spread. `resolvers[]` gives every resolver's answer (`values`, `ttl`, `status` agree / disagree / unavailable), so compare those with the value you published; `records[]` is the most common answer and `analysis.propagation_pct` the share of answering resolvers that gave it (null, like `analysis.record_absent`, when verdict is incomplete). `verdict` is consistent (all agree), absent (all agree there is no record), rotating (a resolver changed its own answer when asked again: load balancing), split_short_ttl (answers differ and every TTL is 300 s or less: CDN or GeoDNS), split (answers differ with no such explanation: finding RESOLVERS_DISAGREE, status warn) or incomplete (fewer than half answered: finding RESOLVERS_PARTIAL, status warn). Otherwise status is info: this tool reports data, not a grade. A timeout is never counted as "no record"; if no resolver answers, the result is a retriable DOH_TIMEOUT error. Not cached, so you can poll it, but it has its own rate limit, lower than the other tools: poll no more often than every 10 seconds, and on error -32029 wait retry_after seconds. Each call queries all 14 resolvers (twice when they disagree). Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: DNS Propagation Checker
check_google_workspaceAudit a domain's DNS against what Google Workspace expects: MX to Google (smtp.google.com, or the legacy aspmx hosts Google still supports), SPF includes _spf.google.com, a DKIM ke…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 Audit a domain's DNS against what Google Workspace expects: MX to Google (smtp.google.com, or the legacy aspmx hosts Google still supports), SPF includes _spf.google.com, a DKIM key at the default google selector (google._domainkey), DMARC policy and rua=, MTA-STS, TLS-RPT and BIMI. Built from the same envelopes check_spf, check_dkim, check_dmarc, check_mx, check_mta_sts, check_tls_rpt and check_bimi return, so it never disagrees with them. `verdict` is configured / configured_with_issues / not_detected / unknown (no indicator found Google Workspace and at least one did not answer). A domain with no Google Workspace indicator (MX, SPF include, google DKIM key) returns only GWS_NOT_DETECTED (status info). A check that could not run is listed in GWS_CHECK_INCOMPLETE and its `analysis.checks[]` entry is `unknown`, never "missing". No key at the google selector is a warning, not a failure, because an admin can choose another prefix: call check_dkim with that selector. Findings include GWS_SPF_NO_GOOGLE_INCLUDE, GWS_SPF_INVALID, GWS_DKIM_DEFAULT_SELECTOR_NOT_FOUND, GWS_DKIM_KEY_WEAK, GWS_DMARC_MISSING, GWS_DMARC_NOT_ENFORCING, GWS_MX_NOT_GOOGLE, GWS_MTA_STS_MISSING, GWS_TLS_RPT_MISSING_UNDER_ENFORCE and more (registry: resources/read mcp://tamingdns/resources/finding-codes). Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Google Workspace DNS Checker
check_m365Audit a domain's DNS against what Microsoft 365 expects: SPF includes spf.protection.outlook.com, DKIM selector1/selector2 (CNAME target and key), DMARC policy and rua=, MX to Micr…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 Audit a domain's DNS against what Microsoft 365 expects: SPF includes spf.protection.outlook.com, DKIM selector1/selector2 (CNAME target and key), DMARC policy and rua=, MX to Microsoft 365 (*.mail.protection.outlook.com or *.mx.microsoft), MTA-STS, Autodiscover to autodiscover.outlook.com, TLS-RPT, BIMI, and the Teams SIP SRV records. Built from the same envelopes check_spf, check_dkim, check_dmarc, check_mx, check_mta_sts, check_tls_rpt and check_bimi return, so it never disagrees with them. `verdict` is configured / configured_with_issues / not_detected / unknown (no indicator found Microsoft 365 and at least one did not answer). A domain with no Microsoft 365 indicator returns only M365_NOT_DETECTED (status info). A check that could not run is listed in M365_CHECK_INCOMPLETE and its `analysis.checks[]` entry is `unknown`, never "missing". Findings include M365_SPF_NO_O365_INCLUDE, M365_SPF_INVALID, M365_DKIM_SELECTOR_MISSING, M365_DKIM_NO_KEY_AT_CNAME, M365_DKIM_CNAME_MISMATCH, M365_DMARC_MISSING, M365_DMARC_NOT_ENFORCING, M365_MX_NOT_M365, M365_MTA_STS_MISSING, M365_AUTODISCOVER_MISSING, M365_TLS_RPT_MISSING_UNDER_ENFORCE and more (registry: resources/read mcp://tamingdns/resources/finding-codes). Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Microsoft 365 DNS Checker
check_mta_stsCheck MTA-STS (RFC 8461) for a domain: the _mta-sts TXT record (strict §3.1 selection — case-sensitive leading v=STSv1, exactly one record, required 1-32 alphanumeric id), the 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 MTA-STS (RFC 8461) for a domain: the _mta-sts TXT record (strict §3.1 selection — case-sensitive leading v=STSv1, exactly one record, required 1-32 alphanumeric id), the policy file at https://mta-sts.<domain>/.well-known/mta-sts.txt fetched WITHOUT following redirects (§3.3), strict §3.2 policy validation (version/mode/max_age required, mx required unless mode none, max_age ≤ 31557600, duplicate keys first-wins), the policy-host X.509 certificate (§3.3 — an invalid cert means compliant senders fetch no policy), and live MX coverage against the mx: patterns (§4.1 — wildcards match exactly one leftmost label; coverage is all/partial/none, partial meaning strict senders skip the uncovered hosts per §5.1). Returns grade (A-F) with grade_reasons, a verdict (enforced/testing/reporting_only/invalid/not_configured), structured findings (MTA_STS_NO_TXT_RECORD, MTA_STS_RECORD_INVALID, MULTIPLE_MTA_STS_RECORDS, MTA_STS_POLICY_UNREACHABLE, MTA_STS_POLICY_REDIRECT, MTA_STS_POLICY_INVALID, MTA_STS_CERT_INVALID, MTA_STS_MODE_NONE, MTA_STS_MODE_TESTING, MTA_STS_MX_MISMATCH, MTA_STS_MX_PARTIAL_COVERAGE, MTA_STS_MAX_AGE_TOO_LOW), and an `analysis` block (record, policy incl. fetch_stage, cert, MX coverage detail, TLS-RPT/DANE cross-signals). Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: MTA-STS Checker
check_spfCheck the SPF record for a domain.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 SPF record for a domain. Returns the raw record, grade (A-F), the terminal `all` qualifier (resolved through redirect= chains), structured findings (NEAR_LOOKUP_LIMIT, LOOKUP_LIMIT_EXCEEDED, PLUS_ALL_DANGEROUS, PTR_MECHANISM_DEPRECATED, etc.), and an `analysis` block with the expanded include/redirect tree and the RFC 7208 §4.6.4 lookup count. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: SPF Record Checker
check_tls_rptCheck the TLS-RPT (SMTP TLS Reporting, RFC 8460) record at _smtp._tls.<domain>.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-RPT (SMTP TLS Reporting, RFC 8460) record at _smtp._tls.<domain>. Strict §3 classification: the record must BEGIN with the case-sensitive v=TLSRPTv1 tag, more than one such record means receivers treat TLS-RPT as not implemented, and rua= is required. Validates every rua= destination syntactically (mailto:/https:// — reachability is never probed), and detects the MTA-STS and DANE prerequisites over DNS (TLSA at _25._tcp of the lowest-preference MX) with outage reported as unknown, never as absence. Returns grade (A-F) with grade_reasons, a verdict (valid/partial/invalid/not_configured), structured findings (TLS_RPT_NO_RECORD, TLS_RPT_INVALID_VERSION, TLS_RPT_MULTIPLE_RECORDS, TLS_RPT_NO_RUA, TLS_RPT_RUA_INVALID_URI, TLS_RPT_NO_VALID_RUA, TLS_RPT_NO_ENFORCEMENT_POLICY), and an `analysis` block with parsed tags, per-URI rua validation detail, and the prerequisite probe results. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: TLS-RPT Checker
check_txtInventory a domain's TXT records and say what is wrong with them.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 Inventory a domain's TXT records and say what is wrong with them. Reads every TXT at the apex and labels each one by vendor or purpose (SPF, Google, Microsoft, Atlassian, Stripe and over a hundred more, grouped into categories), then reads 12 well-known names (_dmarc, _mta-sts, _smtp._tls, default._bimi, _acme-challenge, _amazonses and other provider tokens). Findings: TXT_MULTIPLE_SPF_LIKE (error: more than one v=spf1 record, RFC 7208 §4.5 permerror, so SPF fails for every message), TXT_APEX_DKIM_MISPLACED (error: a DKIM key at the apex, where no verifier looks), TXT_DUPLICATE_TOKEN (warn: the same vendor token twice, usually a stale one), TXT_LOCATIONS_INCOMPLETE (warn: some lookups failed; not evidence of absence) and TXT_NO_RECORDS (info). `verdict` is clean / warnings / misconfigured / incomplete / no_records; no grade. `analysis` carries apex[] (value, ttl, label, category), inventory (category to labels) and locations[] (name, label, status found/absent/failed, values). For a full SPF or DMARC judgement call check_spf or check_dmarc. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: TXT Record Inventory
check_websiteWeb-layer triage of one public hostname, the scan the /website page runs: A/AAAA with reverse DNS and ASN, CAA, the HTTPS redirect chain, the TLS certificate (issuer, SANs, expiry,…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 Web-layer triage of one public hostname, the scan the /website page runs: A/AAAA with reverse DNS and ASN, CAA, the HTTPS redirect chain, the TLS certificate (issuer, SANs, expiry, WebPKI trust, TLS version), security headers (HSTS, CSP, X-Frame-Options, nosniff, Referrer-Policy, Permissions-Policy) and cookie flags, HTTP/2 and HTTP/3 advertisement, whether plain http:// redirects to https, mixed content on the homepage, security.txt, any CDN or WAF in front (analysis.edge) and timings. `verdict` is ok, warn or fail, the same verdict the page shows; `grade_reasons` says why. Findings are one per failing or amber check: WEBSITE_TLS_UNREACHABLE, TLS_CERT_UNTRUSTED, TLS_CERT_HOSTNAME_MISMATCH, TLS_CERT_EXPIRED, WEBSITE_HTTPS_UNREACHABLE, HSTS_MISSING, CSP_MISSING, FRAME_PROTECTION_MISSING, NOSNIFF_MISSING, HTTP_NOT_REDIRECTED_TO_HTTPS, MIXED_CONTENT_ACTIVE (error); TLS_CERT_NEAR_EXPIRY, WEBSITE_NO_HTTP2, HSTS_SHORT_MAX_AGE, HSTS_NO_SUBDOMAINS, CSP_UNSAFE_INLINE, REFERRER_POLICY_MISSING, PERMISSIONS_POLICY_MISSING, HTTP_REDIRECT_NOT_HTTPS, MIXED_CONTENT (warn); WEBSITE_CHALLENGED (info: the homepage was a bot challenge, so headers were not graded). A name that resolves to a private or reserved address is refused with the non-retriable INPUT_INVALID error. One call makes about ten HTTPS requests from our server and can take 30 seconds on a slow site, so it has its own rate limit, lower than the other tools: on error -32029 wait retry_after seconds. Results are cached for 60 seconds. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Website Checker
decode_bounceDecode a pasted bounce: a full NDR email, an SMTP error line or a mail-log fragment.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 Decode a pasted bounce: a full NDR email, an SMTP error line or a mail-log fragment. Finds the SMTP reply code and the enhanced status code (RFC 3463 X.Y.Z), names the provider that sent it (Google, Microsoft, Yahoo, Apple, Comcast, Proofpoint, Mimecast, Barracuda), and returns what the code means and how to fix it. `verdict` is permanent (5xx, finding BOUNCE_PERMANENT, status fail), temporary (4xx, BOUNCE_TEMPORARY, warn), delivered (2xx, pass) or no_code (BOUNCE_NO_CODE, info). When the bounce has no enhanced code, a known phrase in the wording picks the explanation and BOUNCE_CODE_INFERRED says so; analysis.enhanced_code stays null. BOUNCE_AUTH_RELATED marks codes receivers return for SPF, DKIM or DMARC failures: follow up with check_spf, check_dkim and check_dmarc on the sending domain. `analysis.entry` carries the meaning, causes, remediation[] and a link to the code's page, or is null for a code the database does not cover. The echoed `input` is the byte count only. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Email Bounce Decoder
Only reads 6Show 6 read-only tools
analyze_dmarc_reportRead one DMARC aggregate (RUA) report, the XML a receiver sends to the rua= address, pasted as text (decompress a .xml.gz first).Reads text others writeNo findings
Why it is in this group
- The name "analyze_dmarc_report" 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.
Description, as the server wrote it Read one DMARC aggregate (RUA) report, the XML a receiver sends to the rua= address, pasted as text (decompress a .xml.gz first). Returns who reported and when (analysis.report), the policy the domain published (analysis.policy), message totals and the split into DMARC-capable, forwarded (SPF failed, DKIM aligned) and unauthenticated (both failed) mail, every source row with its IP, count, disposition, SPF/DKIM alignment and the sending provider when known (analysis.records, up to 500), and the recommendations the /dmarc-report page shows (analysis.recommendations). `verdict` is unauthenticated_mail, clean or empty_report. Findings: DMARC_REPORT_UNAUTH_NOT_ENFORCED (error: unauthenticated mail under p=none), DMARC_REPORT_UNAUTH_QUARANTINED, DMARC_REPORT_POLICY_UNKNOWN, DMARC_REPORT_LOW_COMPLIANCE, DMARC_REPORT_SP_WEAKER, DMARC_REPORT_RECORDS_SKIPPED (warn), DMARC_REPORT_FORWARDED, DMARC_REPORT_PCT_PARTIAL, DMARC_REPORT_EMPTY (info). A report reflects what receivers saw; check the live record with check_dmarc. Input that is not a <feedback> document, declares a DOCTYPE or is oversize returns the non-retriable INPUT_INVALID error. The echoed `input` is the byte count only; the report is parsed in server memory, not cached and not stored. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: DMARC Aggregate Report Viewer
analyze_email_headersAnalyse a pasted block of raw email headers for spoofing and phishing tells.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "analyze_email_headers" says "analyze": a word for reading.
What it can reach
- private-dataThe name "analyze_email_headers" says "analyze" and "email": it reads mail.
- private-dataThe description's first sentence says "analyse" and "email": it reads mail.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "analyze_email_headers" says "analyze" and "email": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "analyse" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it Analyse a pasted block of raw email headers for spoofing and phishing tells. Input is the raw headers (everything up to the first blank line — "Show original" / "View source"); the message body is not required. Returns structured findings + a phishing verdict (one of likely_phishing, verify_sender, minor_concerns, legitimate, auth_incomplete) derived from SPF/DKIM/DMARC alignment (RFC 7489 §3.1), Microsoft composite-auth compauth reason codes (000/010 enforced failure, 601 intra-org implicit failure, 001 weak posture), ARC chain integrity (RFC 8617 §5.2), homoglyph / IDN look-alike From domains (Unicode UTS #39), header smuggling via duplicate singleton headers (RFC 5322 §3.6), display-name-as-address spoofing, hidden bidi/control characters (UAX #9), Received-chain timestamps running backward (RFC 5321 §4.4), link display-text-vs-href mismatches, originating-IP FCrDNS (RFC 8601), and RFC 8058 List-Unsubscribe deliverability posture (category:compliance, never moves the verdict). Findings include DMARC_FAILED, SPF_HARD_FAIL, DKIM_SIGNATURE_FAILED, COMPAUTH_EXPLICIT_FAILURE, COMPAUTH_INTRA_ORG_IMPLICIT_FAILURE, HOMOGLYPH_DOMAIN, DUPLICATE_HEADER, DISPLAY_NAME_SPOOFED_ADDRESS, RECEIVED_TIMESTAMPS_BACKWARD, URL_DISPLAY_MISMATCH, HIDDEN_CONTROL_CHAR, BRAND_IMPERSONATION, and more (registry: resources/read mcp://tamingdns/resources/finding-codes). `status` is the finding-severity aggregate; `verdict` is the authoritative phishing judgment; `analysis` carries the verdict object + per-mechanism authentication. For privacy the echoed `input` is a digest only (from / subject / message_id) — raw headers are never returned. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Email Header Analyser
check_dnssecValidate a domain's DNSSEC chain of trust.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 a domain's DNSSEC chain of trust. Pulls DS (at the parent), DNSKEY, and RRSIG over binary DoH, walks the chain zone-by-zone (root → TLD → domain) recomputing each DS digest against the published DNSKEYs (RFC 4034 §5.1.4), and cross-checks the AD bit across Cloudflare, Google, Quad9, and OpenDNS so a single resolver's caching can't mask a break. Returns grade (A-F) with grade_reasons, a verdict (signed/signed_no_ds/partial/unsigned/broken), structured findings (DNSSEC_UNSIGNED, DNSSEC_DS_MISSING_AT_PARENT, DNSSEC_DS_ALGORITHM_DEPRECATED, DNSSEC_DNSKEY_ALGORITHM_DEPRECATED, DNSSEC_RRSIG_EXPIRED, DNSSEC_BOGUS, DNSSEC_AD_BIT_MISSING), and an `analysis` block (the full chain-walk, the per-resolver validator matrix, NSEC3 iteration/opt-out, CDS/CDNSKEY publication, signing mode, root-anchor state). Unsigned is the common case and returns status "info" (DNSSEC is optional), not a failure; signed_no_ds (DNSKEY published, no DS at the parent yet) is treated by validators as unsigned and also returns "info"; a published-but-non-validating zone returns "fail". Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: DNSSEC Checker
check_mcp_keysRead the v=MCPv1 TXT records at a domain, the keys the MCP Registry DNS login (mcp-publisher login dns) verifies a signature against, and judge each the way the registry does: v=MC…Reads text others writeNo findings
Why it is in this group
- The description's first verb is "read": 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 Read the v=MCPv1 TXT records at a domain, the keys the MCP Registry DNS login (mcp-publisher login dns) verifies a signature against, and judge each the way the registry does: v=MCPv1; k=<algorithm>; p=<key> in that order and case, k exactly ed25519 or ecdsap384, p padded standard base64 of a 32-byte ed25519 key or a 49-byte compressed P-384 point that lies on the curve. `verdict` is not_configured (info), valid (every record usable, pass), some_invalid (warn), invalid (none usable, fail) or misplaced (fail: no usable record at the domain, but one at _mcp-auth. or _mcp-registry., which the registry never reads; MCP_KEYS_MISPLACED, analysis.misplaced); no grade. Each problem is a warn finding whose title names the key: MCP_KEYS_RECORD_IGNORED, MCP_KEYS_UNKNOWN_ALGORITHM, MCP_KEYS_KEY_NOT_BASE64, MCP_KEYS_KEY_WRONG_LENGTH, MCP_KEYS_ECDSA_NOT_COMPRESSED, MCP_KEYS_ECDSA_NOT_ON_CURVE. MCP_KEYS_NO_VALID_KEY (error) means the login will fail; MCP_KEYS_NO_RECORD (info) means there is no record, and many hosted MCP servers use OAuth instead. `analysis.keys[]` carries algorithm, key length and SHA-256 fingerprint per record; `analysis.apex` names the registrable domain when the input was a subdomain. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: MCP Signing Key Checker
check_mxInspect a domain's MX / mail-routing posture.Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "inspect": a word for reading.
What it can reach
- private-dataThe description's first sentence says "inspect" and "mail": 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 "mail": it reads inbound email, which other people can write.
Description, as the server wrote it Inspect a domain's MX / mail-routing posture. Resolves the apex MX RRset (priority-sorted), and for each host the A/AAAA addresses, PTR + forward-confirmed reverse DNS (FCrDNS), DANE TLSA at _25._tcp.<host>, IP-literal (RFC 5321 §5) and CNAME (RFC 2181 §10.3) violations, and the mail provider. Detects the null MX (RFC 7505), a null MX wrongly mixed with real MX, and the implicit MX via the apex A/AAAA when no MX exists (RFC 5321 §5). Probes the MTA-STS and TLS-RPT prerequisites over DNS (case-sensitive per RFC 8461/8460) with outage reported as unknown, never absence. Returns grade (A-F) with grade_reasons, a verdict (healthy/warnings/misconfigured/null_mx/no_mx/implicit_mx), structured findings (NO_MX_RECORD, MX_IMPLICIT_FALLBACK, NULL_MX, NULL_MX_WITH_OTHER, MX_POINTS_TO_IP, MX_POINTS_TO_CNAME, MX_HOSTNAME_UNRESOLVABLE, NO_PTR_RECORD, FCRDNS_MISMATCH, MX_IPV6_ONLY, MX_NO_TRANSPORT_SECURITY, MX_GATEWAY_RDNS_COSMETIC, MX_SINGLE_HOST, MX_DUPLICATE_HOST, MX_SHARED_PRIORITY, MX_MTA_STS_WITHOUT_TLS_RPT), and an `analysis` block (per-host enrichment incl. provider, ips with FCrDNS status, dane_tlsa, and the prerequisite probe results). DNSSEC AD is a UI-only signal, not gradeable through the DoH contract. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: MX Record Inspector
discover_dkimFind a domain's DKIM keys without knowing the selector.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "find": 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 Find a domain's DKIM keys without knowing the selector. Looks up every selector in the TamingDNS database (over 500, covering Google Workspace, Microsoft 365, SendGrid, Mailchimp, Amazon SES and over 100 other named providers) plus the *._domainkey wildcard, and validates each key it finds the way check_dkim does (KEY_TOO_SHORT, KEY_WEAK, KEY_REVOKED, M365_DKIM_CNAME_MISMATCH and the rest). When the MX is Mimecast it also tries Mimecast's date-stamped selectors: the year selectors (mimecastYYYY) in the call, and, if none holds a key, the dated ones (mimecastYYYYMMDD, about 3,650 names) in a background scan that takes about two minutes. That call says so (DKIM_DISCOVERY_INCOMPLETE, analysis.mimecast.readyAfter); call again after that time. The background outcome is kept for 24 hours (analysis.mimecast.cachedUntil). Returns a grade (A-F) with grade_reasons and a verdict (strong / weak / revoked-only / none / wildcard-revoked / non-sending). `analysis` lists selectors[] with key type and size, providers[], weakKeys[], revokedKeys[], unavailable (lookups that failed) and mimecast. Lookups that failed beside a match raise DKIM_DISCOVERY_INCOMPLETE (warn); the counts are a floor. Failures with no match return the retriable DKIM_LOOKUP_FAILED error, never "no key". A selector outside the database is not found here: read s= from a DKIM-Signature header (analyze_email_headers) and call check_dkim with it. One call is several hundred lookups, so it has its own rate limit. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: DKIM Selector Discovery
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 data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write19
- 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.
Looked at Nov 21, 2026, 19:22 UTC, unchanged since Nov 14, 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
- 13
- Protocol version
- 2025-11-25
- 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 13 tools that change things (13 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://tamingdns.com/mcp: tools/list returned 19 tools to an anonymous client, including check_spf (write), check_dkim (write), check_dmarc (write), check_tls_rpt (write), check_mta_sts (write) and 8 more
Posture changes
- Nov 14, 2026
- Tools that change things, listed without credentials: 7 to 13
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.
PostureRemote posture changed. Tools that change things, listed without credentials: 7 -> 13.View diff
- Tools that change things, listed without credentials: 7 to 13
Tools1 changed.~1 changedView diff
- Changed:check_dns_propagationChanges thingsdescription
Tools1 added, 2 changed.+1 added~2 changedView diff
- Added:discover_dkimOnly reads
- Changed:check_google_workspaceChanges thingsdescription
- Changed:check_m365Changes thingsdescription
Tools5 added, 5 changed.+5 added~5 changedView diff
- Added:analyze_dmarc_reportOnly reads
- Added:check_mcp_keysOnly reads
- Added:check_txtChanges things
- Added:check_websiteChanges things
- Added:decode_bounceChanges things
- Changed:analyze_email_headersOnly readsdescription
- Changed:check_dmarcChanges thingsdescription
- Changed:check_dns_propagationChanges thingsdescription
- Changed:check_google_workspaceChanges thingsdescription
- Changed:check_m365Changes thingsdescription
Tools3 added.+3 addedView diff
- Added:check_dns_propagationChanges things
- Added:check_google_workspaceChanges things
- Added:check_m365Changes things
Install
Pinned to version 2.2.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http tamingdns https://tamingdns.com/mcpclaude mcp add --transport http tamingdns https://tamingdns.com/mcpRun 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.
{
"permissions": {
"allow": [
"mcp__tamingdns__discover_dkim",
"mcp__tamingdns__check_dnssec",
"mcp__tamingdns__check_mx",
"mcp__tamingdns__analyze_dmarc_report",
"mcp__tamingdns__check_mcp_keys",
"mcp__tamingdns__analyze_email_headers"
],
"ask": [
"mcp__tamingdns__check_spf",
"mcp__tamingdns__check_dkim",
"mcp__tamingdns__check_dmarc",
"mcp__tamingdns__check_tls_rpt",
"mcp__tamingdns__check_mta_sts",
"mcp__tamingdns__check_bimi",
"mcp__tamingdns__check_dane",
"mcp__tamingdns__check_m365",
"mcp__tamingdns__check_google_workspace",
"mcp__tamingdns__check_dns_propagation",
"mcp__tamingdns__check_txt",
"mcp__tamingdns__decode_bounce",
"mcp__tamingdns__check_website"
],
"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 tamingdns. Review it before you use it.
Capability tags behind 19 rules
- mcp__tamingdns__check_spf untrusted-input
- mcp__tamingdns__check_dkim untrusted-input
- mcp__tamingdns__discover_dkim untrusted-input
- mcp__tamingdns__check_dmarc untrusted-input
- mcp__tamingdns__check_tls_rpt untrusted-input
- mcp__tamingdns__check_mta_sts untrusted-input
- mcp__tamingdns__check_bimi untrusted-input
- mcp__tamingdns__check_dane untrusted-input
- mcp__tamingdns__check_dnssec untrusted-input
- mcp__tamingdns__check_mx private-data, untrusted-input
- mcp__tamingdns__check_m365 untrusted-input
- mcp__tamingdns__check_google_workspace untrusted-input
- mcp__tamingdns__check_dns_propagation untrusted-input
- mcp__tamingdns__check_txt untrusted-input
- mcp__tamingdns__decode_bounce untrusted-input
- mcp__tamingdns__analyze_dmarc_report untrusted-input
- mcp__tamingdns__check_website untrusted-input
- mcp__tamingdns__check_mcp_keys untrusted-input
- mcp__tamingdns__analyze_email_headers private-data, 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/com.tamingdns/mcp/verify?hash=e85426f9cdde345e497655fe55148fe2ff8eedeeabca6bbe7898f853f5f91eaf" | jq -e '.changed == false'Pinned hash e85426f9cdde, from Nov 14, 2026, 10:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.tamingdns/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.tamingdns/mcp)Source: MCP Registry · repository. Synced Nov 14, 2026, 10:17 UTC.
TamingDNS MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the TamingDNS MCP server safe?
- No scan can promise that. What its definitions show: 19 tools, 13 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 TamingDNS MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the TamingDNS 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 TamingDNS MCP server have?
- 19 tools: 13 write, 6 read. check_spf, check_dkim, check_dmarc, check_tls_rpt, check_mta_sts, check_bimi, check_dane, check_m365 and 11 more.
Does the TamingDNS MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the TamingDNS MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the TamingDNS MCP server changed its tools?
- Yes, 4 times since Anlyon Radar started tracking it, most recently on Nov 14, 2026. Every change is on this page and in its Atom feed.