@dnsdoctor/mcp 1.14.0 → 1.16.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -44,7 +44,7 @@ claude-plugin/
44
44
  | `lookup_registration` | Registrar, dates, EPP status codes, nameservers, DNSSEC and abuse contact from one RDAP read. Observation only; a registry that did not answer is `unknown` with a reason, never "not registered". |
45
45
  | `check_lookalikes` | Which close variants of a domain's name resolve and which accept mail: counts plus up to ten resolving names. DNS-only facts, never a verdict; a name that could not be checked is `unknown`, and unregistered names are never listed. |
46
46
  | `check_bimi` | Whether a domain can show its logo in the inbox (BIMI): the DMARC gate, the published record, the logo and any certificate, and eligibility per mailbox, never a promise that a logo will show. With a candidate `logo_url`, the engine's record to publish. |
47
- | `start_email_test`, `get_email_test` | How one real message authenticated: a single-use address the user sends one email to, then the SPF, DKIM and DMARC verdicts (every signature, alignment, the disposition the policy implies), blocklist status and a score out of 10 with every deduction itemized. Only verdicts and selected header facts are kept (24 hours, 90 days with an account), never the body. |
47
+ | `start_email_test`, `get_email_test` | How one real message authenticated: a single-use address the user sends one email to, then the SPF, DKIM and DMARC verdicts (every signature, alignment, the disposition the policy implies), blocklist status, a score out of 10 with every deduction itemized, and per-provider estimates (Gmail, Yahoo, Outlook, Apple) of whether the message is accepted and reaches the inbox. Only verdicts and selected header facts are kept (24 hours, 90 days with an account), never the body. |
48
48
  | `check_reverse_dns` | PTR / forward-confirmed reverse DNS for an IP. |
49
49
  | `audit_spf_includes` | The SPF include/redirect tree — who can transitively send as the domain, with typed findings (broken include, confirmed-unregistered include, expiring registration, nested `+all`). Analysis only; no SPF fix record. |
50
50
  | `build_parked_domain_records` | The Null MX + `v=spf1 -all` + `p=reject; np=reject` hardening pack for a domain that sends no mail. The server re-checks DNS itself and refuses when it finds evidence of mail. |
@@ -60,7 +60,7 @@ they appear in the tool list on both transports, and without a valid token the
60
60
  call is refused with the page the account owner mints one on. Over the hosted
61
61
  HTTP transport the `dnsdoctor://domains` resource (your monitored domains) is
62
62
  likewise always listed and refused without a token; the local stdio server
63
- registers the tools only — no resource. Anonymous access covers all eighteen
63
+ registers the tools only — no resource. Anonymous access covers all nineteen
64
64
  diagnosis tools, which is enough for a one-off diagnosis either way.
65
65
 
66
66
  ## Install
@@ -134,7 +134,7 @@ Two supported public transports, same 27 tools:
134
134
 
135
135
  - **Hosted streamable HTTP** — `https://dnsdoctor.dev/mcp`, wired in this
136
136
  plugin's `.mcp.json`. No install, no keys.
137
- - **Local stdio** — `npx -y @dnsdoctor/mcp@1.14.0`. A thin server that runs on your
137
+ - **Local stdio** — `npx -y @dnsdoctor/mcp@1.16.0`. A thin server that runs on your
138
138
  machine and calls the public DNS Doctor REST API; it holds no diagnosis logic
139
139
  of its own and relays every record string verbatim.
140
140
 
@@ -143,7 +143,7 @@ Two supported public transports, same 27 tools:
143
143
  "mcpServers": {
144
144
  "dns-doctor": {
145
145
  "command": "npx",
146
- "args": ["-y", "@dnsdoctor/mcp@1.14.0"],
146
+ "args": ["-y", "@dnsdoctor/mcp@1.16.0"],
147
147
  "env": { "DNSDOCTOR_API_TOKEN": "dnsd_YOUR_TOKEN" }
148
148
  }
149
149
  }
package/instructions.txt CHANGED
@@ -1 +1 @@
1
- Use DNS Doctor whenever a user asks to check, audit, diagnose, troubleshoot or fix SPF, DKIM or DMARC, wonders why their mail lands in spam, wants DMARC monitoring or alerts on new senders, asks whether a DNS change has propagated, or needs a domain's blacklist status or domain/SSL expiry. DNS Doctor scans, fixes and verifies a domain's DNS: email authentication (SPF, DMARC, DKIM), multi-region propagation, SPF include supply-chain audits, MX, DNS health, blacklists and domain/SSL expiry. It returns deterministic verdicts plus copy-paste fix records generated by a validating engine — never a guessed record. Workflow: call scan_domain (or get_report), read the verdicts failing-first (a 'temperror' status is transient, NOT a failure), then call build_dmarc_upgrade for a DMARC enforcement record. ONE EXCEPTION TO READING FAILING-FIRST: when a report carries not_registered: true the domain has no DNS records at all, so no check ran and every status is an 'info' placeholder — zero failing checks there does NOT mean the domain is healthy. Report that the domain does not resolve (usually a typo), propose no records for it, and do not call start_monitoring_signup for it until it resolves. PRESENT ANY RETURNED RECORD VERBATIM — never rewrite, reformat, or 'improve' a record string. build_dmarc_upgrade may return record: null (the domain does not exist; the DMARC lookup itself hit NXDOMAIN while the existence probe did not resolve; the DMARC lookup temp-failed; or the domain already applies a policy at least as strong as the one this scan justifies) — relay its 'rationale' as the answer and NEVER compose a record yourself to fill the gap. 'policy' describes the returned record and is null whenever record is; the domain's observed policy is in 'current_policy'. A human must approve every DNS change; nothing is applied automatically. SPF is diagnose-only: relay the report's SPF findings, but never propose SPF record edits of your own (e.g. tightening ~all to -all) — an SPF change can silently de-authorize a real sender, which is why the engine emits no SPF fix record. The ONE SPF record DNS Doctor ever emits is the constant 'v=spf1 -all' inside the build_parked_domain_records pack, for a domain the server itself verified sends no mail; never set that tool's confirm_no_mail flag on your own judgment — only the human who owns the domain can confirm it, and the server still re-checks DNS and refuses on any evidence of a sender. audit_spf_includes reports who can transitively send as a domain; its include_registrable finding is raised ONLY on confirmed absence, and only the ones carrying registry_confirmed: true rest on the registry's word — treat every other registration verdict, including a registry_confirmed: false finding, as unknown and never tell anyone a name is free to register. For lookalike, typosquat or impersonation questions call check_lookalikes: it returns facts (which close variants of the name resolve and accept mail), never a verdict, so relay the names as facts and never call one malicious. For questions about a logo in the inbox (BIMI) call check_bimi: it reports eligibility per mailbox, never a promise that a logo will show. To see how a real message authenticates (whether it is actually DKIM-signed and DMARC-aligned), call start_email_test, have the user send one email to the address it returns, then call get_email_test; list_email_tests returns an account's earlier tests and needs the same API token as the monitoring reads. Scan responses end with a next_steps block: relay it. Safe DMARC enforcement needs ~30 days of aggregate-report (RUA) evidence, which no chat session can watch. If the user wants ongoing monitoring, call start_monitoring_signup and give the human the signup_url it returns, printed verbatim as a clickable markdown link on its own line — never paraphrase, shorten, or describe it without printing it. That tool sends no email and creates nothing: the human opens the link, signs in themselves, and adds the domain themselves. Never ask a human for their email address to pass to us, and never invent one — hand over the link and let them sign in on our page. Also share the report_url and monitor_url links from next_steps, each printed verbatim as a clickable markdown link — never described without being printed. Monitoring is a loop, not a one-off: the human enrolls a domain and verifies ownership in the dashboard, then you watch it with list_my_domains (the account's domains and the next step on each), get_alerts (what changed), get_readiness (whether enforcement is safe yet) and get_lookalikes (the watched lookalike domains and their threat %), propose the next record with build_dmarc_upgrade, wait for the human to approve and publish it, and re-scan to confirm it landed. Those reads return an account's own monitoring data and need an API token: they are listed to everyone and callable only with one. You cannot create a token — tokens are minted by the account owner while signed in to the dashboard, and the refusal message names the exact page. Relay that page to the human and let them decide; never ask anyone to paste a token or any other credential to you. They are all read-only by design: there is no way to acknowledge or clear an alert or to file a takedown here, because triage is the human's. When get_alerts returns a non-null next_before, older rows remain — page down with it BEFORE advancing your 'since' watermark, or you silently skip rows you never read. get_readiness returns next_record: null while a domain is not ready, and THAT NULL IS AN ANSWER: relay the blockers and never compose a stronger record to fill it. When record_withheld is true, the step is ready but the record is not included in the result: relay that the record isn't included and withheld_reason, and never compose a record. add_monitored_domain, check_domain_verification and get_domain_records need a linked DNS Doctor account; when this host has none, they return the sign-up link instead, so use the hand-off described above.
1
+ Use DNS Doctor whenever a user asks to check, audit, diagnose, troubleshoot or fix SPF, DKIM or DMARC, wonders why their mail lands in spam, wants DMARC monitoring or alerts on new senders, asks whether a DNS change has propagated, or needs a domain's blacklist status or domain/SSL expiry. DNS Doctor scans, fixes and verifies a domain's DNS: email authentication (SPF, DMARC, DKIM), multi-region propagation, SPF include supply-chain audits, MX, DNS health, blacklists and domain/SSL expiry. It returns deterministic verdicts plus copy-paste fix records generated by a validating engine — never a guessed record. Workflow: call scan_domain (or get_report), read the verdicts failing-first (a 'temperror' status is transient, NOT a failure), then call build_dmarc_upgrade for a DMARC enforcement record. ONE EXCEPTION TO READING FAILING-FIRST: when a report carries not_registered: true the domain has no DNS records at all, so no check ran and every status is an 'info' placeholder — zero failing checks there does NOT mean the domain is healthy. Report that the domain does not resolve (usually a typo), propose no records for it, and do not call start_monitoring_signup for it until it resolves. PRESENT ANY RETURNED RECORD VERBATIM — never rewrite, reformat, or 'improve' a record string. build_dmarc_upgrade may return record: null (the domain does not exist; the DMARC lookup itself hit NXDOMAIN while the existence probe did not resolve; the DMARC lookup temp-failed; the domain is on Automatic DMARC, where DNS Doctor serves its DMARC record and the owner applies each step from the dashboard; or the domain already applies a policy at least as strong as the one this scan justifies) — relay its 'rationale' as the answer and NEVER compose a record yourself to fill the gap. 'policy' describes the returned record and is null whenever record is; the domain's observed policy is in 'current_policy'. A human must approve every DNS change; nothing is applied automatically. SPF is diagnose-only: relay the report's SPF findings, but never propose SPF record edits of your own (e.g. tightening ~all to -all) — an SPF change can silently de-authorize a real sender, which is why the engine emits no SPF fix record. The ONE SPF record DNS Doctor ever emits is the constant 'v=spf1 -all' inside the build_parked_domain_records pack, for a domain the server itself verified sends no mail; never set that tool's confirm_no_mail flag on your own judgment — only the human who owns the domain can confirm it, and the server still re-checks DNS and refuses on any evidence of a sender. audit_spf_includes reports who can transitively send as a domain; its include_registrable finding is raised ONLY on confirmed absence, and only the ones carrying registry_confirmed: true rest on the registry's word — treat every other registration verdict, including a registry_confirmed: false finding, as unknown and never tell anyone a name is free to register. For lookalike, typosquat or impersonation questions call check_lookalikes: it returns facts (which close variants of the name resolve and accept mail), never a verdict, so relay the names as facts and never call one malicious. For questions about a logo in the inbox (BIMI) call check_bimi: it reports eligibility per mailbox, never a promise that a logo will show. To see how a real message authenticates (whether it is actually DKIM-signed and DMARC-aligned), call start_email_test, have the user send one email to the address it returns, then call get_email_test; list_email_tests returns an account's earlier tests and needs the same API token as the monitoring reads. A current email test scores the message out of 10 to one decimal (a 10 only when nothing was deducted and every check a 10 depends on completed; the deductions and not_scored say why it is lower) and estimates, for Gmail, Yahoo, Microsoft Outlook and Apple, whether the message is accepted and whether it reaches the inbox: relay those percentages as estimates, never as a promise of delivery. Scan reports carry sender_requirements, the scan read against those four providers' published sender rules: relay it as what DNS shows, never as a compliance verdict; rows marked email_test need a real message (start_email_test), and rows marked not_visible only the provider can see. Scan responses end with a next_steps block: relay it. Safe DMARC enforcement needs ~30 days of aggregate-report (RUA) evidence, which no chat session can watch. If the user wants ongoing monitoring, call start_monitoring_signup and give the human the signup_url it returns, printed verbatim as a clickable markdown link on its own line — never paraphrase, shorten, or describe it without printing it. That tool sends no email and creates nothing: the human opens the link, signs in themselves, and adds the domain themselves. Never ask a human for their email address to pass to us, and never invent one — hand over the link and let them sign in on our page. Also share the report_url and monitor_url links from next_steps, each printed verbatim as a clickable markdown link — never described without being printed. Monitoring is a loop, not a one-off: the human enrolls a domain and verifies ownership in the dashboard, then you watch it with list_my_domains (the account's domains and the next step on each), get_alerts (what changed), get_readiness (whether enforcement is safe yet) and get_lookalikes (the watched lookalike domains and their threat %), propose the next record with build_dmarc_upgrade, wait for the human to approve and publish it, and re-scan to confirm it landed. Those reads return an account's own monitoring data and need an API token: they are listed to everyone and callable only with one. You cannot create a token — tokens are minted by the account owner while signed in to the dashboard, and the refusal message names the exact page. Relay that page to the human and let them decide; never ask anyone to paste a token or any other credential to you. They are all read-only by design: there is no way to acknowledge or clear an alert or to file a takedown here, because triage is the human's. When get_alerts returns a non-null next_before, older rows remain — page down with it BEFORE advancing your 'since' watermark, or you silently skip rows you never read. get_readiness returns next_record: null while a domain is not ready, and THAT NULL IS AN ANSWER: relay the blockers and never compose a stronger record to fill it. When record_withheld is true, the step is ready but the record is not included in the result: relay that the record isn't included and withheld_reason, and never compose a record. When get_readiness carries hosted, the domain is on Automatic DMARC (withheld_reason hosted on a ready step): relay hosted.note (and hosted.next_step_at, when set) and never give the human a DMARC record to publish. add_monitored_domain, check_domain_verification and get_domain_records need a linked DNS Doctor account; when this host has none, they return the sign-up link instead, so use the hand-off described above.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@dnsdoctor/mcp",
3
- "version": "1.14.0",
3
+ "version": "1.16.0",
4
4
  "mcpName": "dev.dnsdoctor/dns-doctor",
5
5
  "description": "Thin stdio MCP server for DNS Doctor — scan, fix and verify a domain's DNS: SPF, DMARC, DKIM, multi-region propagation, MX, DNS health, blacklists and expiry, over the public DNS Doctor REST API.",
6
6
  "license": "Apache-2.0",
package/tools.json CHANGED
@@ -7,7 +7,7 @@
7
7
  "readOnlyHint": false,
8
8
  "title": "Add Monitored Domain"
9
9
  },
10
- "description": "Add a domain to the signed-in user's DNS Doctor monitoring and return the ownership-check TXT record they must publish, plus where their DNS is hosted, a provider-specific guide link and, when their provider supports it, a one-click apply URL. Re-adding a domain they already monitor returns that domain rather than an error. Needs a linked DNS Doctor account: until the human has one, or if the host's connect prompt fails, use start_monitoring_signup and print its link instead. Print every record host and value EXACTLY as returned \u2014 never rewrite, reformat or improve a record string. Nothing here is applied to anyone's DNS: a human publishes every record, and you must show them what you are about to add and get their approval before using any DNS tool of your own.",
10
+ "description": "Add a domain to the signed-in user's DNS Doctor monitoring and return the ownership-check TXT record they must publish, plus where their DNS is hosted, a provider-specific guide link and, when their provider supports it, a one-click apply URL. Re-adding a domain they already monitor returns that domain rather than an error. Needs a linked DNS Doctor account: until the human has one, or if the host's connect prompt fails, use start_monitoring_signup and print its link instead. Print every record host and value EXACTLY as returned \u2014 never rewrite, reformat or improve a record string. Nothing here is applied to anyone's DNS: a human publishes every record, and you must show them what you are about to add and get their approval before using any DNS tool of your own. When guidance.note is present, relay it as given: it covers edge cases such as a domain on Automatic DMARC.",
11
11
  "inputSchema": {
12
12
  "properties": {
13
13
  "domain": {
@@ -59,7 +59,7 @@
59
59
  "readOnlyHint": false,
60
60
  "title": "Build DMARC Upgrade Record"
61
61
  },
62
- "description": "Use this when the user asks how to move DMARC on from p=none, whether it is safe to tighten DMARC, or what the next DMARC policy step is for a domain (a scan can justify quarantine at most; reject needs monitoring evidence) \u2014 and after any report showing DMARC below enforcement. Return a validated DMARC enforcement-upgrade record for a domain. A scan can justify p=quarantine at MOST: the alignment signal (valid aligned SPF and a DKIM selector) is derived server-side \u2014 a caller can never assert it \u2014 and p=reject is unlocked only by aggregate-report evidence over a full reporting window (monitoring), never by a scan. `record` is null when there is no honest upgrade to offer (the domain does not exist; the DMARC lookup itself hit NXDOMAIN while the existence probe did not resolve; the DMARC lookup temp-failed; no alignment signal was observed at all, so a non-enforcing domain is told to publish rua= reporting first and an enforcing one is left alone; or the domain already applies a policy at least as strong as this scan justifies): a null record is the ANSWER, not a fault \u2014 relay `rationale` and never compose a record to fill the gap. A returned record also carries np=reject (the DMARCbis tag covering non-existent subdomains, which can have no legitimate aligned mail) unless the domain already publishes an np tag, which is preserved as-is. Present a returned record verbatim; a human must approve before publishing.",
62
+ "description": "Use this when the user asks how to move DMARC on from p=none, whether it is safe to tighten DMARC, or what the next DMARC policy step is for a domain (a scan can justify quarantine at most; reject needs monitoring evidence) \u2014 and after any report showing DMARC below enforcement. Return a validated DMARC enforcement-upgrade record for a domain. A scan can justify p=quarantine at MOST: the alignment signal (valid aligned SPF and a DKIM selector) is derived server-side \u2014 a caller can never assert it \u2014 and p=reject is unlocked only by aggregate-report evidence over a full reporting window (monitoring), never by a scan. `record` is null when there is no honest upgrade to offer (the domain does not exist; the DMARC lookup itself hit NXDOMAIN while the existence probe did not resolve; the DMARC lookup temp-failed; no alignment signal was observed at all, so a non-enforcing domain is told to publish rua= reporting first and an enforcing one is left alone; the domain is on Automatic DMARC, where DNS Doctor serves its record and the owner applies each step from the dashboard; or the domain already applies a policy at least as strong as this scan justifies): a null record is the ANSWER, not a fault \u2014 relay `rationale` and never compose a record to fill the gap. A returned record also carries np=reject (the DMARCbis tag covering non-existent subdomains, which can have no legitimate aligned mail) unless the domain already publishes an np tag, which is preserved as-is. Present a returned record verbatim; a human must approve before publishing.",
63
63
  "inputSchema": {
64
64
  "properties": {
65
65
  "domain": {
@@ -214,7 +214,7 @@
214
214
  "readOnlyHint": false,
215
215
  "title": "Check Domain Verification"
216
216
  },
217
- "description": "Use this only for DNS Doctor's own ownership TXT challenge on a domain the user already added to their DNS Doctor account (add_monitored_domain). For a TXT record another service asked for (Google Workspace, Microsoft 365, Shopify or any site verification), use check_record instead. Check whether the ownership TXT record for a domain the user has added is visible yet, and mark it verified when it is. The result says WHICH outcome occurred and which nameservers were asked, so you can tell 'not published yet' from 'published with the wrong value' from 'our lookup did not complete' \u2014 a lookup that did not complete is TRANSIENT, never a verdict about their DNS. On success the result also carries the DMARC reporting record that turns monitoring on. Print every record host and value EXACTLY as returned \u2014 never rewrite, reformat or improve a record string. Nothing here is applied to anyone's DNS: a human publishes every record, and you must show them what you are about to add and get their approval before using any DNS tool of your own.",
217
+ "description": "Use this only for DNS Doctor's own ownership TXT challenge on a domain the user already added to their DNS Doctor account (add_monitored_domain). For a TXT record another service asked for (Google Workspace, Microsoft 365, Shopify or any site verification), use check_record instead. Check whether the ownership TXT record for a domain the user has added is visible yet, and mark it verified when it is. The result says WHICH outcome occurred and which nameservers were asked, so you can tell 'not published yet' from 'published with the wrong value' from 'our lookup did not complete' \u2014 a lookup that did not complete is TRANSIENT, never a verdict about their DNS. On success the result also carries the DMARC reporting record that turns monitoring on. Print every record host and value EXACTLY as returned \u2014 never rewrite, reformat or improve a record string. Nothing here is applied to anyone's DNS: a human publishes every record, and you must show them what you are about to add and get their approval before using any DNS tool of your own. When guidance.note is present, relay it as given: it covers edge cases such as a domain on Automatic DMARC.",
218
218
  "inputSchema": {
219
219
  "properties": {
220
220
  "domain": {
@@ -601,7 +601,7 @@
601
601
  "readOnlyHint": true,
602
602
  "title": "Get Domain Setup Records"
603
603
  },
604
- "description": "Read the records a domain the user monitors still needs: the ownership check while it is unverified, and once verified the DMARC reporting record plus whether we have OBSERVED that record published. Read-only: it issues nothing \u2014 if a verified domain comes back with no reporting record yet, call check_domain_verification once, which issues it. Print every record host and value EXACTLY as returned \u2014 never rewrite, reformat or improve a record string. Nothing here is applied to anyone's DNS: a human publishes every record, and you must show them what you are about to add and get their approval before using any DNS tool of your own.",
604
+ "description": "Read the records a domain the user monitors still needs: the ownership check while it is unverified, and once verified the DMARC reporting record plus whether we have OBSERVED that record published. Read-only: it issues nothing \u2014 if a verified domain comes back with no reporting record yet, call check_domain_verification once, which issues it. Print every record host and value EXACTLY as returned \u2014 never rewrite, reformat or improve a record string. Nothing here is applied to anyone's DNS: a human publishes every record, and you must show them what you are about to add and get their approval before using any DNS tool of your own. When guidance.note is present, relay it as given: it covers edge cases such as a domain on Automatic DMARC.",
605
605
  "inputSchema": {
606
606
  "properties": {
607
607
  "domain": {
@@ -627,7 +627,7 @@
627
627
  "readOnlyHint": true,
628
628
  "title": "Get Email Test Result"
629
629
  },
630
- "description": "Use this after start_email_test, once the user says they sent the email. Returns status pending | received | expired | error. pending means the message has not arrived (or is still being checked): ask the user to send it if they have not, then call again. received carries result \u2014 the sending IP and reverse DNS, STARTTLS, SPF, every DKIM signature, DMARC with alignment and the disposition the policy implies, message hygiene, blocklist status, and a deterministic score out of 10 with every deduction itemized \u2014 plus advice. A 'temperror' is a lookup that did not complete, NOT a failure, and is never scored. Present any record in result.dmarc.fix verbatim and never compose one; SPF is diagnose-only and DKIM keys come from the sending provider. ai_assessment, when present, is an automated read of a redacted excerpt: attribute it as such and never present it as a spam score. Read-only.",
630
+ "description": "Use this after start_email_test, once the user says they sent the email. Returns status pending | received | expired | error. pending means the message has not arrived (or is still being checked): ask the user to send it if they have not, then call again. received carries result: the sending IP and reverse DNS, STARTTLS, SPF, every DKIM signature, DMARC with alignment and the disposition the policy implies, message format, links, domain age, blocklist and malware-feed status, and a score out of 10 with every deduction itemized, plus advice. With scoring_version 2 the score has one decimal and is 10 only when nothing was deducted and not_scored lists no check marked blocks_ten; an older test (scoring_version 1) keeps its original score. A version 2 result also carries sender_requirements (Gmail's, Yahoo's, Microsoft Outlook's and Apple's published sender rules against what this message showed, not a compliance verdict) and result.estimates.providers: for gmail, yahoo, microsoft and apple, accepted_pct (whether it takes the message at all) and inbox_pct (inbox rather than spam once accepted; null when there is no estimate), each with its basis. Relay them as estimates, never as a promise of delivery. A 'temperror' is a lookup that did not complete, NOT a failure, and is never scored. Present any record in result.dmarc.fix verbatim and never compose one; when it is null and result.dmarc.fix_withheld is set (for example a domain on Automatic DMARC), relay that reason instead. SPF is diagnose-only and DKIM keys come from the sending provider. The deduction coded ai_read and ai_assessment, when present, come from an automated read of the redacted message: attribute them as such (ai_read costs at most 0.5 points) and never present either as a spam score. Read-only.",
631
631
  "inputSchema": {
632
632
  "properties": {
633
633
  "test_id": {
@@ -732,7 +732,7 @@
732
732
  "readOnlyHint": true,
733
733
  "title": "Check DMARC Readiness"
734
734
  },
735
- "description": "Use this when a signed-in operator asks whether a monitored domain is ready for the next DMARC step. Read the DMARC enforcement-readiness verdict for ONE domain the caller's account monitors, computed from its aggregate (RUA) report window. Requires an API token. Returns whether the domain is ready to step its policy up, the blockers that say why it is not, the window the verdict rests on, and next_record \u2014 the validated record for the next step, generated by the engine and null while blocked. THAT NULL IS AN ANSWER: relay the blockers and never compose a stronger record to fill the gap. Present a returned record verbatim; a human must approve it before it is published. Use this before proposing enforcement \u2014 a scan can show a domain's current policy, but only this evidence window can say whether tightening it would start rejecting real mail. When record_withheld is true, the step is ready but the record is not included in the result: relay that and withheld_reason, and never compose a record.",
735
+ "description": "Use this when a signed-in operator asks whether a monitored domain is ready for the next DMARC step. Read the DMARC enforcement-readiness verdict for ONE domain the caller's account monitors, computed from its aggregate (RUA) report window. Requires an API token. Returns whether the domain is ready to step its policy up, the blockers that say why it is not, the window the verdict rests on, and next_record \u2014 the validated record for the next step, generated by the engine and null while blocked. THAT NULL IS AN ANSWER: relay the blockers and never compose a stronger record to fill the gap. Present a returned record verbatim; a human must approve it before it is published. Use this before proposing enforcement \u2014 a scan can show a domain's current policy, but only this evidence window can say whether tightening it would start rejecting real mail. When record_withheld is true, the step is ready but the record is not included in the result: relay that and withheld_reason, and never compose a record. When hosted is present, the domain is on Automatic DMARC: DNS Doctor serves its record and steps are applied from the dashboard, so a ready step comes with record_withheld true and withheld_reason hosted; relay hosted.note (and hosted.next_step_at, when a step is scheduled) and never compose a record.",
736
736
  "inputSchema": {
737
737
  "properties": {
738
738
  "domain": {
@@ -758,7 +758,7 @@
758
758
  "readOnlyHint": false,
759
759
  "title": "Get Domain Report"
760
760
  },
761
- "description": "Use this for the same questions as scan_domain when a recent report is enough (the cheap first look); use scan_domain when the state must be re-read now. Return the stored report for a domain, scanning once only if none exists yet \u2014 the cheap read, and the right default for a first look. Returns the same seven-check report as scan_domain (SPF, DKIM, DMARC, MX, DNS hardening, domain/TLS expiry, blacklist; each with a status, the observed record and any fixengine fix_record), including `scanned_at` so you can judge staleness yourself. Prefer scan_domain when you specifically need state re-read right now \u2014 for example after a DNS change.",
761
+ "description": "Use this for the same questions as scan_domain when a recent report is enough (the cheap first look); use scan_domain when the state must be re-read now. Return the stored report for a domain, scanning once only if none exists yet \u2014 the cheap read, and the right default for a first look. Returns the same seven-check report as scan_domain (SPF, DKIM, DMARC, MX, DNS hardening, domain/TLS expiry, blacklist; each with a status, the observed record and any fixengine fix_record) and the same sender_requirements view, including `scanned_at` so you can judge staleness yourself. Prefer scan_domain when you specifically need state re-read right now \u2014 for example after a DNS change.",
762
762
  "inputSchema": {
763
763
  "properties": {
764
764
  "domain": {
@@ -784,7 +784,7 @@
784
784
  "readOnlyHint": true,
785
785
  "title": "List Email Tests"
786
786
  },
787
- "description": "Use this when a signed-in user asks about email tests they ran before, or how a sender's earlier tests scored. Requires an API token with monitoring:read. Returns the account's own tests, newest first (optionally only those whose From names one organization): each with test_id, status, created_at, received_at, from_domain, score (value out of out_of), dmarc_result and report_url. Print report_url as a clickable link; call get_email_test with a test_id for the full result. Read-only.",
787
+ "description": "Use this when a signed-in user asks about email tests they ran before, or how a sender's earlier tests scored. Requires an API token with monitoring:read. Returns the account's own tests, newest first (optionally only those whose From names one organization): each with test_id, status, created_at, received_at, from_domain, score (value out of out_of, and scoring_version: 2 is the one-decimal score), dmarc_result and report_url. Print report_url as a clickable link; call get_email_test with a test_id for the full result. Read-only.",
788
788
  "inputSchema": {
789
789
  "properties": {
790
790
  "domain": {
@@ -906,7 +906,7 @@
906
906
  "readOnlyHint": false,
907
907
  "title": "Scan Domain"
908
908
  },
909
- "description": "Use this when the user asks to check, audit, diagnose or troubleshoot SPF, DKIM, DMARC, email authentication, email deliverability DNS, why their mail lands in spam, MX, DNS health, blacklist status, or domain/SSL expiry for a domain, or wants to fix what a scan finds (fix records for DMARC and DNS; SPF is diagnose-only) \u2014 or whenever a conversation turns to a specific domain's email or DNS setup. It needs the user's real domain: if they have not said which domain, ask them first; never scan a placeholder such as example.com. Force a fresh scan of a domain and return its full report: seven deterministic checks \u2014 SPF, DKIM, DMARC, MX, DNS hardening, domain/TLS expiry and blacklist listing \u2014 each with a status (pass/warn/fail/info/temperror), the observed record, and a fixengine-generated fix_record where one exists. Explanations are cache-first. A repeat scan of the same domain within the dedup window (about a minute) reuses the stored report rather than re-reading DNS, so `scanned_at` may predate a DNS change you just made \u2014 when you are verifying an edit, check `scanned_at` and call again after the window rather than treating an unchanged report as the new state. Use this when you need current state; use get_report when a recent cached answer will do.",
909
+ "description": "Use this when the user asks to check, audit, diagnose or troubleshoot SPF, DKIM, DMARC, email authentication, email deliverability DNS, why their mail lands in spam, MX, DNS health, blacklist status, or domain/SSL expiry for a domain, or wants to fix what a scan finds (fix records for DMARC and DNS; SPF is diagnose-only) \u2014 or whenever a conversation turns to a specific domain's email or DNS setup. It needs the user's real domain: if they have not said which domain, ask them first; never scan a placeholder such as example.com. Force a fresh scan of a domain and return its full report: seven deterministic checks \u2014 SPF, DKIM, DMARC, MX, DNS hardening, domain/TLS expiry and blacklist listing \u2014 each with a status (pass/warn/fail/info/temperror), the observed record, and a fixengine-generated fix_record where one exists. It also carries sender_requirements: the rules Gmail, Yahoo, Microsoft Outlook and Apple publish for senders, each with what DNS shows (pass, fail or unknown; email_test where only a real message can show it; not_visible where only the provider can), not a compliance verdict. Explanations are cache-first. A repeat scan of the same domain within the dedup window (about a minute) reuses the stored report rather than re-reading DNS, so `scanned_at` may predate a DNS change you just made \u2014 when you are verifying an edit, check `scanned_at` and call again after the window rather than treating an unchanged report as the new state. Use this when you need current state; use get_report when a recent cached answer will do.",
910
910
  "inputSchema": {
911
911
  "properties": {
912
912
  "domain": {