12 MCP tools. Email verification, sender reputation, DNSBL, SPF/DKIM/DMARC analysis, inbox-placement scoring. Drop into Claude Desktop in 60 seconds.
Already have a Min8T account? Sign in to claim a key.
Add to claude_desktop_config.json
// ~/Library/Application Support/Claude/claude_desktop_config.json { "mcpServers": { "deliveriq": { "command": "npx", "args": ["-y", "@deliveriq/mcp"], "env": { "DELIVERIQ_API_KEY": "lc_your_key" } } } }
21 checks across 5 stages, run in parallel where possible. Sub-3-second per email.
RFC 5322 compliance check. Validates structure, character set, and the @-placement before any network calls.
Sift3 fuzzy match against a database of 1,200+ common misspellings of popular providers (e.g. gmial.com → gmail.com).
Continuously maintained list of 164,000+ throwaway-email domains.
Flags 130+ role prefixes (admin@, info@, support@, noreply@…) with lower engagement and higher bounce rates.
Identifies Gmail, Yahoo, Outlook, and 200+ other consumer email domains worldwide. Useful when corporate addresses are required.
Resolves +tag and dot-aliases to canonical form (user+news@gmail.com → user@gmail.com) so duplicates collapse.
Scores the local-part for entropy, keyboard walks, and bot-style sequences. Distinguishes human-typed from auto-generated.
DNS MX lookup with A-record fallback. Highest-priority server is used for SMTP. Capped at top 2 to prevent timeout stacking.
MX-pattern match against known ISPs. Major providers that block SMTP probes are skipped intelligently for accuracy and speed.
Real conversation: TCP 25 connect → EHLO → MAIL FROM → RCPT TO. Second RCPT with a random address detects catch-alls. 5-second timeout. No email is sent.
A Gravatar profile is a positive trust signal: someone set up a public identity with this address.
47 categorized zones (Spamhaus, SpamCop, SURBL, URIBL, SORBS, Barracuda, UCEProtect, DroneBL…) plus domain-based lists.
Registration date, expiration, registrar, DNSSEC, nameservers. Domains under 30 days are high-risk; under a year, elevated.
Have I Been Pwned lookup. Compromised addresses are more likely to be abandoned or spam-targeted.
Probes 15 common DKIM selectors in parallel. Returns key type (RSA / Ed25519) and estimated key size when found.
SPF + DKIM + DMARC policy + MTA-STS + BIMI + TLS-RPT. Composite score out of 100. A full stack scores highest.
Reverse-DNS (PTR) and IP-DNSBL on the MX itself. Servers without PTR or with blacklisted IPs indicate lower-quality infrastructure.
12 weighted signals (age, role, no Gravatar, SMTP, disposable, DNSBL, catch-all, entropy, MX rep, IP blacklist, pattern type). Classifies trap as Pristine / Recycled / Typo with confidence.
0–100 composite: age (25) + infrastructure (25) + reputation (25) + trust signals like DNSSEC and registrar lock (25). Maps to Trusted / Positive / Neutral / Suspicious / Malicious.
Single 0–100 number combining SMTP, reputation, infrastructure, spam-trap probability, and address characteristics. The model gets one actionable verdict.
Score maps to Safe (80–100) / Risky (40–79) / Invalid (1–39) / Unknown (0). Unknown captures timeouts, greylisting, and catch-all servers.
Every email gets a single 0–100 score, mapped to one of four categories.
Structured input, structured output. The model decides what to call when.
Single-email verification. Syntax, MX, SMTP, DNSBL, SPF/DKIM/DMARC, score.
1 creditSubmit a batch for async verification. Downloadable CSV results.
1 / emailPoll batch progress and per-category breakdown.
freeDownload finished batch as CSV. Filterable by category.
freePaginated list of recent verification jobs.
freeFind a business email by name and domain. Pattern-aware.
2 creditsScan a domain across 50 DNSBL zones. Per-zone result.
1 creditSPF, DKIM, DMARC, MTA-STS, BIMI analysis with composite score.
1 creditEvaluate spam-trap risk for an email. 13 weighted signals.
1 creditComposite trust report. MX, DNSBL, infra, age, ISP.
1 creditCached organization intelligence. Email patterns, contact count.
freePlan, balance, monthly usage, daily breakdown.
freeDeliverability is the kind of problem where the right answer needs 6 to 8 API calls in sequence. Verify, then DMARC, then blocklist, then sender reputation. Letting the model orchestrate as tools is roughly 10× more useful than another dashboard. It can plan, branch on results, and explain the verdict in plain English.
Sign up, generate a key, paste into Claude Desktop. Five minutes from cold open to first verification.
Get my API key