WarmInboxes Free Deliverability Tools
Free cold email deliverability checks, list tools, inbox planning and original placement research.
Should I use this
Quality & Safety
Findings (5)
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domainin spamhaus_dbl_guidance
- MEDIUMTool description contains URL to non-standard domainin burned_inbox_guidance
- MEDIUMTool description contains URL to non-standard domainin cold_email_writing_resources
- MEDIUMTool description contains URL to non-standard domainin find_lead_lists
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"deliverability-tools": {
"url": "https://warminboxes.com/mcp"
}
}
}Remote endpoints
https://warminboxes.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (51)
🟢check_deliverability(domain)
Grade a domain A-F for cold email readiness. Checks SPF, DKIM, DMARC, MX, blacklists and domain age together and returns a weighted score with a per-check breakdown and what to fix. Start here for open-ended "is this domain any good" questions.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain to grade, e.g. \"acme.com\". Not an email address."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢check_spf(domain)
Look up a domain's SPF record and validate it, including the recursive DNS lookup count that silently breaks SPF past 10.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain to check, e.g. \"acme.com\"."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢check_dkim(domain, selector)
Find and validate a domain's DKIM signing key, including key strength. Leave selector empty to auto-scan 26 common selectors (google, selector1, k1, and the rest). When no key is found, reports whether the selectors are delegated by CNAME to a provider that has not published one — the usual Microsoft 365 failure, where the records are right but signing was never switched on.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain to check, e.g. \"acme.com\"."
},
"selector": {
"type": "string",
"description": "Optional DKIM selector. Omit to auto-scan common selectors."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢check_dmarc(domain)
Look up and parse a domain's DMARC record: policy, subdomain policy, percentage, alignment and reporting tags, each explained. p=none (monitoring) passes: it meets Google and Yahoo's requirement and is fine for broad cold email. p=quarantine is the step for stricter enforcement; do not tell someone p=none is broken.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain to check, e.g. \"acme.com\"."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢check_bimi(domain)
Validate a domain's BIMI record, the logo SVG, the VMC, and the DMARC enforcement level Gmail requires before it will show a brand logo.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain to check, e.g. \"acme.com\"."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢check_mta_sts(domain)
Validate a domain's _mta-sts DNS record and its published policy file: mode, MX patterns, max_age and TLS-RPT.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain to check, e.g. \"acme.com\"."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢check_ssl(domain, port)
Read a host's TLS certificate: issuer, validity dates and days remaining, subject alternative names, key type and size, signature algorithm, chain, negotiated protocol and whether the chain is trusted and covers the hostname. Use it on an MTA-STS policy host (mta-sts.<domain>) or a click-tracking domain, where an expired certificate stops mail or turns every click into a browser warning. Port 25 is not reachable from serverless, so the certificate an MX host presents cannot be read this way.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Hostname to read a certificate from, e.g. \"mta-sts.acme.com\". A URL or host:port is accepted."
},
"port": {
"type": "number",
"description": "TCP port. Defaults to 443. Port 25 is rejected: outbound SMTP is blocked."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢check_dns(domain, type)
Query any DNS record type for a domain: MX, TXT, A, AAAA, CNAME, NS, SOA, CAA.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain to query, e.g. \"acme.com\"."
},
"type": {
"type": "string",
"description": "Record type, e.g. \"MX\", \"TXT\", \"A\". Defaults to MX if omitted."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢lookup_txt(domain)
Every TXT record on a domain, with each one identified (SPF, DKIM, DMARC, MTA-STS, TLS-RPT, BIMI, or which service's ownership token it is), plus the four underscore names a receiver reads — _dmarc, _mta-sts, _smtp._tls and default._bimi — in the same lookup. Names the three mistakes that are invisible from reading the records: more than one SPF record, which makes a receiver return permerror so SPF fails entirely; a DMARC or DKIM record published at the apex, where nothing will ever read it; and a record longer than one 255-byte TXT string. Use this before concluding a record is missing, because the usual cause of a missing DMARC record is a DMARC record at the wrong name.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain to read TXT records from, e.g. \"acme.com\". A name beginning with an underscore, such as \"_dmarc.acme.com\", is read on its own."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢check_rdns(ip)
The PTR record for an IPv4 or IPv6 address, and the forward lookup that decides whether it counts. Reverse DNS is delegated to whoever holds the address block, so a PTR alone proves nothing — the operator of an IP can point it at any hostname, including one they do not own. Only the round trip is evidence: PTR names a host, that host resolves back to the same address. That pair is forward-confirmed reverse DNS (FCrDNS), it is what Google and Yahoo mean when they list forward and reverse DNS among their bulk sender requirements, and it is what `fcrdns` reports. Over IPv6 it is stricter still: Gmail rejects IPv6 mail from an address without it, where the same mail over IPv4 would be accepted. Reports a missing PTR separately from a PTR that fails to confirm, because the fixes differ and only the address block's operator — usually the hosting provider, not the sender — can set either.
Input Schema
{
"type": "object",
"properties": {
"ip": {
"type": "string",
"description": "An IPv4 or IPv6 address, e.g. \"8.8.8.8\" or \"2001:4860:4860::8888\". Not a hostname."
}
},
"required": [
"ip"
],
"additionalProperties": false
}🟢check_blacklist(input)
Check a domain or IP against 20+ major email blacklists (Spamhaus, Barracuda, SORBS and others) and report which list it appears on.
Input Schema
{
"type": "object",
"properties": {
"input": {
"type": "string",
"description": "A domain or an IPv4 address."
}
},
"required": [
"input"
],
"additionalProperties": false
}🟢check_surbl(domains)
Check domains against the SURBL URI blacklist in bulk. URI blacklists list the domains that appear inside a message body, so a listed tracking or landing domain sends the whole email to spam however clean the sender is. Up to 100 domains per call.
Input Schema
{
"type": "object",
"properties": {
"domains": {
"type": "array",
"items": {
"type": "string"
},
"description": "Domains to check. Max 100."
}
},
"required": [
"domains"
],
"additionalProperties": false
}🟢check_nameservers(domains)
Get the NS records and the DNS provider behind one domain or a whole list. Useful for working out who actually controls a domain's DNS before trying to fix its records.
Input Schema
{
"type": "object",
"properties": {
"domains": {
"type": "array",
"items": {
"type": "string"
},
"description": "Domains to look up."
}
},
"required": [
"domains"
],
"additionalProperties": false
}🟢check_domain_expiry(domain)
Get a domain's registrar, creation date, expiry date and days remaining, over RDAP with a WHOIS fallback for ccTLDs that publish no RDAP service. Domain age is one of the strongest cold-email risk signals.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain to look up, e.g. \"acme.com\"."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢check_google_domain(domain)
Tell whether a domain is already attached to a Google Workspace account, or is clear for a fresh Google tenant.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain to check, e.g. \"acme.com\"."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢check_cname(host, expected)
Follow a host's full CNAME chain and flag the mistakes that break a cold-email tracking domain. Pass expected to assert where the chain should end up.
Input Schema
{
"type": "object",
"properties": {
"host": {
"type": "string",
"description": "Hostname to follow, e.g. \"track.acme.com\"."
},
"expected": {
"type": "string",
"description": "Optional target the chain should resolve to."
}
},
"required": [
"host"
],
"additionalProperties": false
}🟢verify_email(emails)
Check email addresses for syntax, live MX records, disposable providers and role prefixes (info@, sales@). Does not open SMTP connections, so catch-all domains come back valid.
Input Schema
{
"type": "object",
"properties": {
"emails": {
"type": "array",
"items": {
"type": "string"
},
"description": "Email addresses to verify."
}
},
"required": [
"emails"
],
"additionalProperties": false
}🟢lookup_mx(domain, domains)
Look up a domain's MX records with priorities and resolved IPs, and identify the mailbox provider (Google Workspace, Microsoft 365, Zoho, Fastmail and others) and any security gateway in front of it (Mimecast, Proofpoint, Barracuda and others). Pass `domains` instead of `domain` for up to 100 at once, which also returns a provider breakdown. Reports a null MX (RFC 7505) rather than treating it as a broken record, and does not guess the provider behind a gateway, because that is not observable from the MX.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "A single domain, e.g. \"acme.com\". An address like \"[email protected]\" is accepted."
},
"domains": {
"type": "array",
"items": {
"type": "string"
},
"description": "Up to 100 domains, instead of `domain`."
}
},
"required": [],
"additionalProperties": false
}🟢segment_esp(domains)
Split a list of domains by the email provider behind them (Google, Microsoft, or a security gateway) from their MX records. Sending Google-to-Google and Microsoft-to-Microsoft is one of the larger levers on inbox placement.
Input Schema
{
"type": "object",
"properties": {
"domains": {
"type": "array",
"items": {
"type": "string"
},
"description": "Domains to segment."
}
},
"required": [
"domains"
],
"additionalProperties": false
}🟢plan_from_list(domains, emailsPerDay, prewarmed, microsoftEsp, billing, ...)
Estimates a sending fleet for a recipient list. Looks up the MX records of up to 100 recipient domains (or addresses) to measure the Google / Microsoft / other mix, then sizes a Google Workspace pool for the Google recipients and an Azure pool (Microsoft 365 with microsoftEsp) for the Microsoft ones: inbox count, domain count, per-inbox pace and monthly cost for each, plus totals. Recipients that are neither (gateways, self-hosted, no MX) are added to the Google pool and their share is reported, because what sits behind a gateway cannot be seen from MX. For a longer list, send a sample: the estimate follows the provider split, not the list length. Assumes no reserve capacity. A planning estimate only: it does not provision or order anything. The result describes how an order is placed: a first order in the WarmInboxes app, later ones through the WarmInboxes purchasing API.
Input Schema
{
"type": "object",
"properties": {
"domains": {
"type": "array",
"items": {
"type": "string"
},
"description": "Up to 100 recipient domains or email addresses. Deduplicated."
},
"emailsPerDay": {
"type": "number",
"description": "Target cold emails per day across the whole list, e.g. 1500."
},
"prewarmed": {
"type": "boolean",
"description": "true for prewarmed inboxes (sending within 48–72 hours of delivery), false for fresh (21-day warmup, cheaper). Defaults to true."
},
"microsoftEsp": {
"type": "string",
"enum": [
"azure",
"microsoft"
],
"description": "Which pool carries the Microsoft recipients. Defaults to azure."
},
"billing": {
"type": "string",
"enum": [
"monthly",
"twoMonth",
"quarterly"
],
"description": "Prewarmed commitment length. Longer is cheaper. Defaults to monthly."
},
"rotation": {
"type": "boolean",
"description": "Rest half the fleet at any moment, which doubles the inboxes bought. Defaults to false."
}
},
"required": [
"domains",
"emailsPerDay"
],
"additionalProperties": false
}🟢plan_infrastructure(emailsPerDay, esp, prewarmed, billing, emailsPerMailbox, ...)
Estimates how many inboxes and domains a daily cold email volume needs and the monthly cost at WarmInboxes' published prices. Inputs: emailsPerDay; optionally the provider (esp), prewarmed or fresh, billing cycle, emails per inbox per day and inboxes per domain. With dealValue (and optionally closeRate and positiveRate) it adds a revenue and ROI projection from those inputs. Assumes the provider's default daily pace per inbox unless emailsPerMailbox is given, and 22 sending days a month. The result is a planning estimate: it orders nothing, does not guarantee placement or replies, and its revenue figures follow only from the rates supplied.
Input Schema
{
"type": "object",
"properties": {
"emailsPerDay": {
"type": "number",
"description": "Target cold emails per day, e.g. 500."
},
"esp": {
"type": "string",
"enum": [
"google",
"microsoft",
"azure"
],
"description": "Sending platform. Defaults to google."
},
"prewarmed": {
"type": "boolean",
"description": "true for prewarmed inboxes (ready to send on delivery), false for fresh (14-21 day warmup, about a third the price). Defaults to true."
},
"billing": {
"type": "string",
"enum": [
"monthly",
"twoMonth",
"quarterly"
],
"description": "Prewarmed commitment length. Longer cycles are cheaper. Defaults to monthly. Google and Microsoft are billed per inbox; Azure is billed per tenant, flat, whatever is on the tenant."
},
"emailsPerMailbox": {
"type": "number",
"description": "Daily sends per inbox. Defaults to the platform's safe pace: 15 Google, 8 Microsoft, 2 Azure."
},
"mailboxesPerDomain": {
"type": "number",
"description": "Fresh Google and Microsoft only. Defaults to 3."
},
"inboxesPerTenant": {
"type": "number",
"enum": [
25,
50,
100
],
"description": "Fresh Azure only: how densely a tenant is packed. Also sets the pace, since a lighter tenant sends more per inbox (25/6, 50/4, 100/2). Defaults to 100."
},
"rotation": {
"type": "boolean",
"description": "Rest half the fleet at any moment, which doubles the inboxes bought. Defaults to false."
},
"dealValue": {
"type": "number",
"description": "Average deal size. Supply it to get replies, deals, revenue and ROI."
},
"closeRate": {
"type": "number",
"description": "Percent of positive replies that close. Defaults to 10."
},
"positiveRate": {
"type": "number",
"description": "Percent of sends that reply positively. Defaults to 1."
}
},
"required": [
"emailsPerDay"
],
"additionalProperties": false
}🟢quote_inboxes(inboxes, provider, prewarmed, billing)
Prices a given number of inboxes at WarmInboxes' published prices: the domains (or Azure tenants) they sit on, daily sending capacity at the provider's pace, monthly cost and delivery time. Use it when the person already knows the count ("preview 100 inboxes"); for a send volume use plan_infrastructure. Azure is sold by the tenant, so a count that does not fill one is quoted for the tenants it needs, with a note. A quote only: it orders nothing, and the exact preview with real domain and mailbox names is in the app or on the purchasing server.
Input Schema
{
"type": "object",
"properties": {
"inboxes": {
"type": "number",
"description": "How many inboxes, 1 to 20,000."
},
"provider": {
"type": "string",
"enum": [
"google",
"microsoft",
"azure"
],
"description": "Google Workspace, Microsoft 365, or Azure (Microsoft tenants). Defaults to google."
},
"prewarmed": {
"type": "boolean",
"description": "true for prewarmed inboxes, false for fresh (14-21 day warmup, cheaper). Defaults to true."
},
"billing": {
"type": "string",
"enum": [
"monthly",
"twoMonth",
"quarterly"
],
"description": "Prewarmed commitment length. Longer is cheaper. Defaults to monthly."
}
},
"required": [
"inboxes"
],
"additionalProperties": false
}🟢expand_spintax(template, vars, samples)
Expand a spintax template such as "{Hi|Hey} there" and render its Liquid merge tags, returning the total number of variations, every variable the template references, any variable with no value and no default, and a set of rendered samples. Use it to check a sequence before it sends.
Input Schema
{
"type": "object",
"properties": {
"template": {
"type": "string",
"description": "The template, with {spin|groups} and {{merge_tags}}."
},
"vars": {
"type": "object",
"description": "Values for the merge tags, e.g. {\"first_name\": \"Sarah\"}."
},
"samples": {
"type": "number",
"description": "How many variations to render, 1 to 25. Defaults to 3."
}
},
"required": [
"template"
],
"additionalProperties": false
}🟢generate_unsubscribe(company, address, unsubUrl, style, tone)
Build a CAN-SPAM and GDPR compliant opt-out footer in plain text and HTML, with a checklist saying which compliance requirements the details given actually satisfy. A footer with no postal address is the usual failure.
Input Schema
{
"type": "object",
"properties": {
"company": {
"type": "string",
"description": "Sender name, as it should appear."
},
"address": {
"type": "string",
"description": "Physical postal address. Required by CAN-SPAM."
},
"unsubUrl": {
"type": "string",
"description": "Unsubscribe link, for the link and both styles."
},
"style": {
"type": "string",
"enum": [
"reply",
"link",
"both"
],
"description": "How someone opts out. Defaults to reply."
},
"tone": {
"type": "string",
"enum": [
"casual",
"formal"
],
"description": "Defaults to casual."
}
},
"required": [],
"additionalProperties": false
}🟢check_email_authentication(domain)
SPF, DKIM, DMARC, MX, BIMI and MTA-STS for one domain in one call, each judged pass, weak, fail or not set, with the essentials separated from the optional records. BIMI and MTA-STS are optional and come back "absent", never failed. Use it when someone has been told to "fix their email authentication" and does not know which record that means.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain, e.g. \"acme.com\"."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢check_domain_reputation(domain)
For "this domain used to land and now it does not". Checks the domain against SURBL, its authentication, its age and the address its website resolves to, and returns a verdict by elimination (listed, broken, young, clean or unknown) with what it rules out. No reputation score: receivers hold that privately. The Spamhaus DBL needs a paid key and is reported as not checked, never as clean.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain, e.g. \"acme.com\"."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢check_tracking_domain(host, sendingDomain)
Check the domain a campaign's tracked links point at: whether it resolves, serves a valid certificate, is listed on SURBL, sits on a listed address, belongs under the sending domain, and whether it is a platform's shared tracking host. A listed tracking domain is in the body of every message, which is what content filters hash.
Input Schema
{
"type": "object",
"properties": {
"host": {
"type": "string",
"description": "The tracking domain, e.g. \"click.acme.com\"."
},
"sendingDomain": {
"type": "string",
"description": "Optional: the domain the mail is sent from, to check the tracker sits under it."
}
},
"required": [
"host"
],
"additionalProperties": false
}🟢check_bulk_sender_requirements(domain, ip, headers)
The bulk sender requirements, sorted honestly: SPF, DKIM, DMARC and MX checked from DNS; forward and reverse DNS when given the sending IP; one-click unsubscribe and From alignment when given a received message's raw headers; and the requirements no outside tool can see (complaint rate, per-connection TLS) named as not checked rather than passed.
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Sending domain, e.g. \"acme.com\"."
},
"ip": {
"type": "string",
"description": "Optional: the sending IP, only if they run their own mail server."
},
"headers": {
"type": "string",
"description": "Optional: raw headers of a message they sent, as received, to check one-click unsubscribe and alignment."
}
},
"required": [
"domain"
],
"additionalProperties": false
}🟢analyze_headers(headers)
Read a received message's raw headers. Returns the SPF, DKIM and DMARC verdicts the receiver recorded, which domains authenticated and whether they align with the From domain (why DMARC failed on a message that "passed"), the relay hops and delays, the sending IP, plain-English issues, and whether the List-Unsubscribe headers satisfy one-click (RFC 8058). Text only: nothing is looked up or stored.
Input Schema
{
"type": "object",
"properties": {
"headers": {
"type": "string",
"description": "The raw header block of a received message (Gmail: ⋮ → Show original)."
}
},
"required": [
"headers"
],
"additionalProperties": false
}🟢analyze_email_html(html, scan)
Read an email's HTML. Returns its size against Gmail's ~102 KB clipping limit with what is taking the room, every link and image host, tracking pixels, URL shorteners, and each linked domain checked against SURBL. Parsed inertly: nothing loads, no pixel fires, no link is followed. The SURBL lookups count against the daily free limit; set scan to false to skip them.
Input Schema
{
"type": "object",
"properties": {
"html": {
"type": "string",
"description": "The full HTML of the email."
},
"scan": {
"type": "boolean",
"description": "Check the linked domains against SURBL. Defaults to true."
}
},
"required": [
"html"
],
"additionalProperties": false
}🟢analyze_dmarc_report(xml, gzipBase64)
Read DMARC aggregate (rua) reports and say who is sending as the domain and what fails: messages passing and failing, failures that are alignment only, quarantined and rejected counts, and each sending IP with its SPF and DKIM outcome, failing senders first. Takes the report XML, several of them, or a .gz report as base64. Duplicate reports are counted once.
Input Schema
{
"type": "object",
"properties": {
"xml": {
"type": "string",
"description": "The report XML. To send several, call with gzipBase64 or repeat the call; a JSON array of XML strings is also accepted over HTTP."
},
"gzipBase64": {
"type": "string",
"description": "A gzipped report (.xml.gz), base64-encoded. Zip archives are not unpacked: send the XML inside."
}
},
"required": [],
"additionalProperties": false
}🟢analyze_cold_email(subject, body)
Score a cold email's copy 0-100 for spam risk before it is sent: weighted trigger words by category and severity (subject hits weigh extra), ALL-CAPS, links and shorteners, currency and percent-off offers, obfuscated spellings, missing personalisation or opt-out, length. Returns each finding with how much it cost and how to fix it. Content only: it cannot see reputation or authentication.
Input Schema
{
"type": "object",
"properties": {
"subject": {
"type": "string",
"description": "The subject line. Optional, but subject-line triggers weigh extra."
},
"body": {
"type": "string",
"description": "The email body as plain text, merge tags included."
}
},
"required": [
"body"
],
"additionalProperties": false
}🟢audit_campaign(csv, sequence, inboxes, perInbox, daysPerWeek, ...)
Audit a cold email campaign before launch: the lead CSV and the sequence checked together for merge tags with no column or empty values, variable syntax the sequencer will not parse, role and disposable addresses, duplicates and too many contacts per company, plus a send forecast from the sending settings. Pass the CSV text and every step of the sequence.
Input Schema
{
"type": "object",
"properties": {
"csv": {
"type": "string",
"description": "The lead CSV as text, header row first."
},
"sequence": {
"type": "string",
"description": "Every step of the sequence, merge tags as written, e.g. {{first_name}}."
},
"inboxes": {
"type": "number",
"description": "Sending inboxes. Defaults to 5."
},
"perInbox": {
"type": "number",
"description": "Sends per inbox per day. Defaults to 30."
},
"daysPerWeek": {
"type": "number",
"enum": [
5,
7
],
"description": "Sending days a week. Defaults to 5."
},
"stepGapDays": {
"type": "number",
"description": "Days between steps. Defaults to 3."
},
"maxPerCompany": {
"type": "number",
"description": "Contacts allowed per company domain. Defaults to 2."
}
},
"required": [
"csv",
"sequence"
],
"additionalProperties": false
}🟢analyze_bounces(bounces)
Classify bounce messages (NDRs): invalid address, full or disabled mailbox, reputation block, authentication failure, throttling, content block or configuration, each with whether it is hard, soft or a block, why it happened and what to do. Separate several bounces with a blank line.
Input Schema
{
"type": "object",
"properties": {
"bounces": {
"type": "string",
"description": "One or more bounce messages as pasted text, separated by a blank line or ---."
}
},
"required": [
"bounces"
],
"additionalProperties": false
}🟢analyze_microsoft_headers(headers)
Read the spam verdict Microsoft 365 or Outlook stamped on a delivered message: SCL (spam confidence), BCL (bulk), PCL, SFV, the category, and the SPF, DKIM, DMARC and composite authentication results, each explained. Use it when mail lands in Outlook junk. For Gmail or any provider's routing and alignment, use analyze_headers.
Input Schema
{
"type": "object",
"properties": {
"headers": {
"type": "string",
"description": "The full raw headers of a message delivered to a Microsoft mailbox."
}
},
"required": [
"headers"
],
"additionalProperties": false
}🟢preview_inbox(subject, fromName, body)
Show how a cold email's sender name, subject line and preview text are cut off in Gmail desktop, Gmail mobile and Outlook, with warnings (no sender name, all caps, empty preview, etc.). Use it to check a subject line fits before sending.
Input Schema
{
"type": "object",
"properties": {
"subject": {
"type": "string",
"description": "The subject line."
},
"fromName": {
"type": "string",
"description": "The sender name as recipients see it."
},
"body": {
"type": "string",
"description": "The email body; its first text becomes the preview snippet."
}
},
"required": [
"subject"
],
"additionalProperties": false
}🟢generate_dns_records(spfProviders, spfIncludes, spfMx, spfAll, dmarcPolicy, ...)
Write an SPF record from the providers that send for a domain (with an estimate of its DNS lookups against the limit of 10), a DMARC record from a policy, and where a provider publishes DKIM. Returns host, type and value to publish. It writes records; to check what is published, use check_spf, check_dmarc and check_dkim.
Input Schema
{
"type": "object",
"properties": {
"spfProviders": {
"type": "array",
"items": {
"type": "string"
},
"description": "Providers that send for the domain, e.g. [\"Google Workspace\", \"SendGrid\"]."
},
"spfIncludes": {
"type": "array",
"items": {
"type": "string"
},
"description": "Extra SPF include domains, e.g. [\"_spf.example.com\"]."
},
"spfMx": {
"type": "boolean",
"description": "Add the mx mechanism. Defaults to false."
},
"spfAll": {
"type": "string",
"enum": [
"-all",
"~all",
"?all"
],
"description": "Policy for unlisted senders. Defaults to ~all."
},
"dmarcPolicy": {
"type": "string",
"enum": [
"none",
"quarantine",
"reject"
],
"description": "Ask for a DMARC record with this policy. p=none is fine for cold email."
},
"dmarcRua": {
"type": "string",
"description": "Address for aggregate reports, e.g. [email protected]."
},
"dmarcPct": {
"type": "string",
"enum": [
"100",
"50",
"25",
"10"
],
"description": "Percentage the policy applies to. Defaults to 100."
},
"dmarcSubdomainPolicy": {
"type": "string",
"enum": [
"none",
"quarantine",
"reject"
],
"description": "Subdomain policy, if different."
},
"dkimProvider": {
"type": "string",
"description": "A provider to get DKIM setup steps for, e.g. \"Google Workspace\"."
}
},
"required": [],
"additionalProperties": false
}🟢plan_rotation(sendsPerDay, inboxes, cadenceWeeks)
Suggests a two-batch inbox rotation schedule: the fleet split in half, one batch sending while the other rests, swapped every 1, 2 or 4 weeks. Returns batch sizes, the daily load per active inbox compared with a 15-a-day pace, how many inboxes the volume needs at that pace, and an eight-week calendar. A suggested schedule only: it does not pause, resume or change any inbox or sequencer.
Input Schema
{
"type": "object",
"properties": {
"sendsPerDay": {
"type": "number",
"description": "Cold emails sent per day."
},
"inboxes": {
"type": "number",
"description": "Inboxes in the fleet."
},
"cadenceWeeks": {
"type": "number",
"enum": [
1,
2,
4
],
"description": "Weeks between swaps. Defaults to 2."
}
},
"required": [
"sendsPerDay",
"inboxes"
],
"additionalProperties": false
}🟢plan_verification_waterfall(listSize, verifiers)
Price an email verification waterfall: the list run through verifiers in sequence with unknowns passed down the chain, every order compared, cheapest cost per usable email first. Uses typical figures for three verifiers unless you pass your own prices and resolve rates (POST JSON for verifiers).
Input Schema
{
"type": "object",
"properties": {
"listSize": {
"type": "number",
"description": "Emails on the list."
},
"verifiers": {
"type": "array",
"description": "Optional: up to 5 verifiers with pricePer1k (USD), resolvePct (share given a definite answer) and validOfResolvedPct (share of those that are valid).",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"pricePer1k": {
"type": "number"
},
"resolvePct": {
"type": "number"
},
"validOfResolvedPct": {
"type": "number"
}
},
"required": [
"pricePer1k",
"resolvePct",
"validOfResolvedPct"
]
}
}
},
"required": [
"listSize"
],
"additionalProperties": false
}🟢clean_csv(csv, removeRole, removeDisposable)
Clean a lead CSV: malformed, duplicate, role-based (info@, sales@) and disposable addresses removed, with a count for each reason. Returns the cleaned CSV when it is 500 rows or fewer; a larger file is summarised and the person is sent to the page to download the full result. Does not verify mailboxes exist.
Input Schema
{
"type": "object",
"properties": {
"csv": {
"type": "string",
"description": "The lead CSV as text, header row first, with an email column."
},
"removeRole": {
"type": "boolean",
"description": "Remove role addresses. Defaults to true."
},
"removeDisposable": {
"type": "boolean",
"description": "Remove disposable-domain addresses. Defaults to true."
}
},
"required": [
"csv"
],
"additionalProperties": false
}🟢convert_csv(csv, platform)
Rename a lead CSV's columns to the fields a sequencer imports (Instantly, Smartlead, EmailBison, or generic snake_case). Every row and column is kept; only the header changes, and columns with no standard field keep a snake_case name for custom variables. Returns the mapping, and the converted CSV when it is 500 rows or fewer.
Input Schema
{
"type": "object",
"properties": {
"csv": {
"type": "string",
"description": "The lead CSV as text, header row first."
},
"platform": {
"type": "string",
"enum": [
"instantly",
"smartlead",
"emailbison",
"generic"
],
"description": "The sequencer to import into."
}
},
"required": [
"csv",
"platform"
],
"additionalProperties": false
}🟢combine_csvs(files, dedupe, addSource)
Merge several lead CSVs into one, matching columns that mean the same thing (Email, email_address, E-mail), optionally removing duplicate emails and adding a column for the file each row came from. Returns the combined CSV when it is 500 rows or fewer. POST JSON: files is an array.
Input Schema
{
"type": "object",
"properties": {
"files": {
"type": "array",
"description": "2 to 20 files, each { name, csv }.",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"csv": {
"type": "string"
}
},
"required": [
"csv"
]
}
},
"dedupe": {
"type": "boolean",
"description": "Remove duplicate emails. Defaults to true."
},
"addSource": {
"type": "boolean",
"description": "Add a source-file column. Defaults to true."
}
},
"required": [
"files"
],
"additionalProperties": false
}🟢check_suppression(csv, suppression, suppressionCsv, matchDomains, maxPerCompany)
Check a campaign list against a do-not-contact list before sending: exact email matches and, optionally, whole suppressed domains, with a per-company cap. Returns what was removed and why, and the clean CSV when it is 500 rows or fewer.
Input Schema
{
"type": "object",
"properties": {
"csv": {
"type": "string",
"description": "The campaign CSV as text, header row first."
},
"suppression": {
"type": "string",
"description": "Addresses and domains not to contact, one per line."
},
"suppressionCsv": {
"type": "string",
"description": "Or the do-not-contact list as a CSV."
},
"matchDomains": {
"type": "boolean",
"description": "A suppressed domain removes everyone at it. Defaults to true."
},
"maxPerCompany": {
"type": "number",
"description": "Cap contacts per company domain; 0 for no cap. Defaults to 0."
}
},
"required": [
"csv"
],
"additionalProperties": false
}🟢spamhaus_dbl_guidance(domain)
Explains how to check a domain on the Spamhaus Domain Block List by hand at https://check.spamhaus.org. Does not query the Spamhaus DBL (it needs a paid key) and never returns a listing verdict: the result states that nothing was checked, gives Spamhaus's own lookup, and names the blocklist checks this server does run (check_surbl, check_blacklist).
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "The domain asked about."
}
},
"required": [],
"additionalProperties": false
}🟢burned_inbox_guidance(domain)
Directs the person to the external Burned Inbox Checker at https://burnedinbox.com. Does not itself determine whether an inbox or domain is burned; the result gives the link and names the checks here that answer part of the question (check_domain_reputation, check_deliverability).
Input Schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "The domain or inbox asked about."
}
},
"required": [],
"additionalProperties": false
}🟢cold_email_writing_resources
Directs the person to Cold Email AI, the WarmInboxes cold email writing assistant at https://warminboxes.com/AI (a custom GPT on ChatGPT). Does not generate email copy itself; the result gives the link and names the tools here that check a draft (analyze_cold_email, preview_inbox, expand_spintax).
Input Schema
{
"type": "object",
"properties": {},
"required": [],
"additionalProperties": false
}🟢find_lead_lists(query, category, limit)
Searches WarmInboxes' own catalogue of about 1,000 free B2B lead lists, by industry, role and country, as published at https://warminboxes.com/leads. It does not search the web or any other database. Returns the best-matching lists with lead counts, verified email counts and each list's page. Lists are emailed to the person from that page; this tool cannot request or download a list.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "What they want, in plain words: an industry, role or country, e.g. \"SaaS founders UK\" or \"dentists\"."
},
"category": {
"type": "string",
"description": "Optional category to narrow to, e.g. \"Accountants\". Call with no query to get the category list."
},
"limit": {
"type": "number",
"description": "How many matches, 1 to 10. Defaults to 3."
}
},
"required": [],
"additionalProperties": false
}🟢find_tools(task, callableOnly, limit)
Find the WarmInboxes free tool for a task ("check my email headers", "clean a CSV", "will this land in spam") and say how to use it: the MCP tool to call here, or the page to send the person to when it runs only in the browser. Call with no task to list every tool.
Input Schema
{
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "The job, in plain words, e.g. \"find which DKIM selectors a domain uses\"."
},
"callableOnly": {
"type": "boolean",
"description": "Only tools you can call from this server. Defaults to false."
},
"limit": {
"type": "number",
"description": "How many matches, 1 to 10. Defaults to 5."
}
},
"required": [],
"additionalProperties": false
}🟢find_resources(query, type, limit)
Search what WarmInboxes publishes: cold email guides, deliverability playbooks, original studies and their datasets, costed infrastructure recipes, tool demo videos, inbox guides per sequencer and AI agent, provider comparisons, Claude skills, the changelog, and the offer and about pages. Searches titles and full text, and each match carries the passage that best answers the query. It holds WarmInboxes' own measurements (monthly inbox placement tests, sender reputation by TLD, a SURBL study) as well as guides. read_resource returns a whole page.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "A question or topic, e.g. \"warming up Azure inboxes\" or \"Smartlead\"."
},
"type": {
"type": "string",
"enum": [
"guide",
"playbook",
"study",
"dataset",
"recipe",
"video",
"inbox-guide",
"comparison",
"skill",
"changelog",
"company"
],
"description": "Optional: only this kind of resource."
},
"limit": {
"type": "number",
"description": "How many matches, 1 to 10. Defaults to 5."
}
},
"required": [],
"additionalProperties": false
}🟢read_resource(url, part)
Read a WarmInboxes guide, study, playbook, dataset, recipe, comparison or changelog entry in full, as markdown. Long pages come in parts split at headings: the first call says how many, and nextPart gives the one to ask for. Datasets also return their data as JSON. Use the url find_resources gave you.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The page, as find_resources returned it, e.g. \"https://warminboxes.com/research/inbox-placement-log\". A path works too."
},
"part": {
"type": "number",
"description": "Which part of a long page, from 1. Defaults to 1."
}
},
"required": [
"url"
],
"additionalProperties": false
}🟢get_pricing
The WarmInboxes price list as data: prewarmed and fresh inboxes on Google Workspace, Microsoft 365 and Azure, every billing cycle, the safe daily send pace per inbox, and delivery time. For a costed fleet for a volume, use plan_infrastructure.
Input Schema
{
"type": "object",
"properties": {},
"required": [],
"additionalProperties": false
}Community
Evidence