@dnsdoctor/mcp 1.21.1 → 1.22.0

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
@@ -1,35 +1,39 @@
1
- # @dnsdoctor/mcp: DNS Doctor as a local stdio MCP server
1
+ # DNS Doctor: get your domain's email working, and know it stays that way
2
2
 
3
3
  [![mcptry](https://mcptry.com/badge/dev.dnsdoctor/dns-doctor)](https://mcptry.com/servers/dev.dnsdoctor/dns-doctor) [![DNS Doctor MCP server – quality and maintenance score on Glama](https://glama.ai/mcp/servers/dnsdoctor/mcp/badges/score.svg)](https://glama.ai/mcp/servers/dnsdoctor/mcp) [![mcp.market](https://mcp.market/badge/dnsdoctor-dns-doctor.svg)](https://mcp.market/server/dnsdoctor-dns-doctor) [![npm](https://img.shields.io/npm/v/@dnsdoctor/mcp)](https://www.npmjs.com/package/@dnsdoctor/mcp) [![npm downloads](https://img.shields.io/npm/dm/@dnsdoctor/mcp)](https://www.npmjs.com/package/@dnsdoctor/mcp) [![DNS Doctor MCP on mcprush](https://mcprush.com/badge/dns-doctor-mcp/score.svg)](https://mcprush.com/to/dns-doctor-mcp?ref=badge)
4
4
 
5
- A thin MCP server that runs on your machine and calls the public
6
- [DNS Doctor](https://dnsdoctor.dev) REST API. It exposes the same 29 tools as the
7
- hosted server at `https://dnsdoctor.dev/mcp`: scan a domain's email
8
- authentication (SPF, DMARC, DKIM), MX, DNS health, blacklists and domain/SSL
9
- expiry, check propagation, and get the exact fix record to publish.
5
+ See why mail lands in spam, get the exact DNS record to fix it, and check the change
6
+ is live everywhere.
10
7
 
11
- It holds no diagnosis logic of its own and relays every record string verbatim.
12
- Every fix record comes from DNS Doctor's deterministic engine, never from a model
13
- guess.
8
+ DNS Doctor checks a domain's email setup (SPF, DKIM, DMARC), mail routing, DNS
9
+ health, blacklists and domain/SSL expiry, and tells your AI assistant what is
10
+ wrong in plain words. When a record needs fixing it returns the exact record to
11
+ copy and paste. That record comes from a validating engine, never from a model
12
+ guess, and nothing is ever changed in your DNS for you.
14
13
 
15
- Most clients should use the hosted server instead (no install, no keys):
14
+ Scanning and fixes are free: no account, no key, no card.
16
15
 
17
- ```json
18
- { "mcpServers": { "dns-doctor": { "type": "http", "url": "https://dnsdoctor.dev/mcp" } } }
19
- ```
16
+ ## Ask your assistant
20
17
 
21
- For Claude Code, the [DNS Doctor plugin](https://github.com/dnsdoctor/claude-plugin)
22
- wires the hosted server and adds the skills.
18
+ - "Why do emails from example.com land in spam?"
19
+ - "Check SPF, DKIM and DMARC for example.com and give me the record to fix what fails."
20
+ - "I just changed my MX records. Is the change live everywhere yet?"
21
+ - "Is example.com on any blacklist, and when do its domain and SSL certificate expire?"
22
+ - "Is it safe to move example.com from p=none to p=quarantine?"
23
23
 
24
- ## Run it
24
+ ## Install
25
+
26
+ This package runs on your machine and calls the public
27
+ [DNS Doctor](https://dnsdoctor.dev) API. It has the same 29 tools as the hosted
28
+ server and holds no diagnosis logic of its own: every record string is relayed
29
+ verbatim.
25
30
 
26
31
  ```json
27
32
  {
28
33
  "mcpServers": {
29
34
  "dns-doctor": {
30
35
  "command": "npx",
31
- "args": ["-y", "@dnsdoctor/mcp@1.21.1"],
32
- "env": { "DNSDOCTOR_API_TOKEN": "dnsd_YOUR_TOKEN" }
36
+ "args": ["-y", "@dnsdoctor/mcp@1.22.0"]
33
37
  }
34
38
  }
35
39
  }
@@ -38,6 +42,28 @@ wires the hosted server and adds the skills.
38
42
  Node 20 or newer. Pin the version as shown, so the code you run is the code you
39
43
  reviewed.
40
44
 
45
+ If your client supports remote servers, the hosted one needs no install at all:
46
+
47
+ ```json
48
+ { "mcpServers": { "dns-doctor": { "type": "http", "url": "https://dnsdoctor.dev/mcp" } } }
49
+ ```
50
+
51
+ For Claude Code, the [DNS Doctor plugin](https://github.com/dnsdoctor/claude-plugin)
52
+ wires the hosted server and adds the skills.
53
+
54
+ ## Monitoring (optional)
55
+
56
+ A scan is a snapshot. [Monitoring](https://dnsdoctor.dev/pricing) watches your
57
+ domains every day, reads your DMARC reports, emails you when something breaks
58
+ and tells you when it is safe to tighten DMARC. With an account, your assistant
59
+ can also list your monitored domains, alerts and readiness.
60
+
61
+ Add a token to use the account tools:
62
+
63
+ ```json
64
+ "env": { "DNSDOCTOR_API_TOKEN": "dnsd_YOUR_TOKEN" }
65
+ ```
66
+
41
67
  - `DNSDOCTOR_API_TOKEN` is optional. Anonymous access covers scanning and fixes;
42
68
  the account tools (monitored domains, alerts, readiness, lookalike watches,
43
69
  email tests) need a token. Create one at dnsdoctor.dev under
package/instructions.txt CHANGED
@@ -1 +1 @@
1
- Use DNS Doctor whenever a user asks to check, diagnose or fix SPF, DKIM or DMARC, wonders why their mail lands in spam, wants DMARC or website uptime monitoring, asks whether a DNS change has propagated, or needs a domain's blacklist status or 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) and read the verdicts failing-first (a 'temperror' status is transient, NOT a failure). ONE EXCEPTION: when a report carries not_registered: true the domain has no DNS records, so every status is an 'info' placeholder and zero failing checks does NOT mean the domain is healthy. Say the domain does not resolve (usually a typo), and propose no records and no start_monitoring_signup for it until it resolves. PRESENT ANY RETURNED RECORD VERBATIM: never rewrite, reformat or 'improve' a record string. When a tool returns record: null, that null is the answer: relay its 'rationale' and NEVER compose a record yourself to fill the gap. Scan responses end with a next_steps block: relay it, and print its report_url and monitor_url verbatim as clickable markdown links, never described without being printed. When 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. The human opens it, signs in and adds the domain themselves. Never ask a human for their email address to pass to us, and never invent one. 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 edits of your own (e.g. ~all to -all), because an SPF change can silently de-authorize a real sender (the parked-domain pack's 'v=spf1 -all' is the one exception). Most users are not DNS experts: explain each finding in plain words (what it means for their mail) and gloss technical terms. Add at most one short fact per reply, only one your DNS Doctor skill lists for that finding, never one of your own (and none where the result card shows its own tip). In build_dmarc_upgrade, 'policy' describes the returned record and is null whenever record is; the observed policy is 'current_policy'. Safe DMARC enforcement needs about 30 days of aggregate-report (RUA) evidence, which no chat session can watch, so monitoring is a loop: once the human has added and verified a domain, watch it with list_my_domains, get_alerts (what changed), get_readiness and get_lookalikes, propose the next record with build_dmarc_upgrade, let the human approve and publish it, and re-scan to confirm it landed. These reads are read-only by design: clearing an alert or filing a takedown is the human's own triage. They need an API token, which only the account owner can mint in the dashboard (you cannot create one); the refusal names the page. Relay it and never ask anyone to paste a token or any other credential to you. When get_alerts returns a non-null next_before, page down with it BEFORE advancing your 'since' watermark, or you silently skip rows. 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. With record_withheld true, the step is ready but the record is not included: relay withheld_reason and never compose it. With hosted set, the domain is on Automatic DMARC: relay hosted.note (and hosted.next_step_at) 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 this host cannot make: use the hand-off above.
1
+ Use DNS Doctor whenever a user asks to check, diagnose or fix SPF, DKIM or DMARC, wonders why their mail lands in spam, wants DMARC or website uptime monitoring, asks whether a DNS change has propagated, or needs a domain's blacklist status or domain/SSL expiry. It returns deterministic verdicts plus copy-paste fix records from a validating engine, never a guessed record. Workflow: call scan_domain (or get_report) and read the verdicts failing-first (a 'temperror' status is transient, NOT a failure). ONE EXCEPTION: when a report carries not_registered: true the domain has no DNS records, so every status is an 'info' placeholder and zero failing checks does NOT mean the domain is healthy. Say the domain does not resolve (usually a typo), and propose no records and no start_monitoring_signup until it resolves. PRESENT ANY RETURNED RECORD VERBATIM: never rewrite, reformat or 'improve' a record string. When a tool returns record: null, that null is the answer: relay its 'rationale' and NEVER compose a record to fill the gap. Scan responses end with a next_steps block: relay it, and print its report_url and monitor_url verbatim as clickable markdown links, never just described. When 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. The human opens it, signs in and adds the domain themselves. Never ask a human for their email address to pass to us, and never invent one. 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 edits of your own, because an SPF change can silently de-authorize a real sender (the parked-domain pack's 'v=spf1 -all' is the one exception). Explain each finding in plain words (what it means for their mail), glossing technical terms. Add at most one short fact per reply, only one your DNS Doctor skill lists for that finding, never one of your own (none where the result card shows its own tip). In build_dmarc_upgrade, 'policy' describes the returned record (null whenever record is); the observed policy is 'current_policy'. Safe DMARC enforcement needs about 30 days of RUA report evidence, so monitoring is a loop: once a domain is added and verified, watch it with list_my_domains, get_alerts, get_readiness and get_lookalikes, propose the next record with build_dmarc_upgrade, let the human publish it, and re-scan to confirm it landed. Clearing an alert or filing a takedown is the human's own triage. They need an API token, which only the account owner can mint in the dashboard; the refusal names the page. Relay it and never ask anyone to paste a token or any other credential. When get_alerts returns a non-null next_before, page down with it BEFORE advancing your 'since' watermark, or you skip rows. 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. With record_withheld true, relay withheld_reason and never compose it. With hosted set (Automatic DMARC), relay hosted.note (and hosted.next_step_at) and never give the human a DMARC record. Pending-domain results may add dns_host (name_fields: what to type as the Name), agent (follow agent.says; ask the user before any DNS change), diagnosis.causes (why a check missed: relay each says), help.share_url (a page for whoever runs the DNS) and guidance.website_file (a website file proving ownership instead of the TXT record). add_monitored_domain, check_domain_verification and get_domain_records need a linked DNS Doctor account this host cannot make: use the hand-off above.
package/package.json CHANGED
@@ -1,8 +1,8 @@
1
1
  {
2
2
  "name": "@dnsdoctor/mcp",
3
- "version": "1.21.1",
3
+ "version": "1.22.0",
4
4
  "mcpName": "dev.dnsdoctor/dns-doctor",
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.",
5
+ "description": "DNS Doctor MCP server (stdio): find out why a domain's email lands in spam, get the exact DNS record to fix it and check the change is live everywhere. SPF, DMARC, DKIM, MX, propagation, blacklists and expiry, over the public DNS Doctor REST API.",
6
6
  "license": "Apache-2.0",
7
7
  "author": {
8
8
  "name": "DNS Doctor",
@@ -46,7 +46,7 @@
46
46
  "devDependencies": {
47
47
  "@types/node": "^22.15.0",
48
48
  "typescript": "^5.9.2",
49
- "vitest": "4.1.11"
49
+ "vitest": "4.1.12"
50
50
  },
51
51
  "overrides": {
52
52
  "hono": ">=4.13.5"