OutboundAuth Deliverability

Free SPF, DKIM, DMARC, blacklist, MX and bounce checks for any domain, as MCP tools for AI agents.

Should I use this

Quality & Safety

A
Description quality
98%
Schema completeness
98%
Naming quality
100%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~1,387Tokens (tool definitions)
~525 BTypical response size
Moderate attention impact (1.08% of 128k context)

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": {
    "outboundauth": {
      "url": "https://outboundauth.com/mcp"
    }
  }
}

Remote endpoints

https://outboundauth.com/mcpstreamable-http

What it can do

Tool inventory

Tools (10)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢check_spf(domain)

Look up the live SPF TXT record for a domain and evaluate it: version tag, default policy (-all vs ~all), the 10-DNS-lookup limit, PTR use. Returns a scored verdict with findings.

Input Schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Domain to check, e.g. example.com"
    }
  },
  "required": [
    "domain"
  ]
}
🟢check_dmarc(domain)

Look up the live DMARC TXT record at _dmarc.<domain> and evaluate it: policy (none/quarantine/reject), aggregate reporting (rua). Returns a scored verdict with findings.

Input Schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Domain to check, e.g. example.com"
    }
  },
  "required": [
    "domain"
  ]
}
🟢check_dkim(domain, selector)

Look up the live DKIM TXT record for a selector (<selector>._domainkey.<domain>) and evaluate the key: version, key type, public key presence. Follows CNAMEs (e.g. Microsoft 365 / Google selectors).

Input Schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Domain to check, e.g. example.com"
    },
    "selector": {
      "type": "string",
      "description": "DKIM selector, e.g. google, selector1, s1 (ask the email provider if unknown)"
    }
  },
  "required": [
    "domain",
    "selector"
  ]
}
🟢check_email_auth(domain)

Run the complete deliverability authentication check for a domain: SPF, DMARC, DKIM (probes common selectors), and MX records. Returns a scored verdict per area plus an overall summary.

Input Schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Domain to check, e.g. example.com"
    }
  },
  "required": [
    "domain"
  ]
}
🟢analyze_bounce(bounce_text, code)

Explain an email bounce in plain English: paste the full bounce message or just the error (e.g. "550 5.7.1"). Returns whether it is a hard or soft bounce, what happened, the likely cause (list quality, reputation, policy, authentication, temporary), and the fix.

Input Schema

{
  "type": "object",
  "properties": {
    "bounce_text": {
      "type": "string",
      "description": "The full bounce message or the error text from the sending tool"
    },
    "code": {
      "type": "string",
      "description": "Just the bounce code, e.g. 550 or 550 5.7.1 (alternative to bounce_text)"
    }
  }
}
🟢check_blacklists(domain, ip)

Check a domain's sending IPs (resolved from its mail servers) and/or a specific IP against 7 major DNS blacklists (Spamhaus ZEN, SpamCop, PSBL, UCEPROTECT, Mailspike, DroneBL, UBL). Reports listed or clean per list, per IP.

Input Schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Domain whose mail-server IPs should be checked, e.g. example.com"
    },
    "ip": {
      "type": "string",
      "description": "A specific IPv4 address to check, e.g. 192.0.2.10"
    }
  }
}
🟢check_mx_health(domain)

Look up a domain's MX records and evaluate them: priorities, whether each mail server resolves, the likely mail provider (Google Workspace, Microsoft 365, …), and obvious misconfigurations. Returns a scored verdict with findings.

Input Schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Domain to check, e.g. example.com"
    }
  },
  "required": [
    "domain"
  ]
}
🟢analyze_email_headers(headers)

Explain raw email headers in plain English: the Authentication-Results verdicts for SPF, DKIM and DMARC (with the domains each check covered), From vs Return-Path alignment, and the Received hop count. Paste the full headers ("Show original" in Gmail).

Input Schema

{
  "type": "object",
  "properties": {
    "headers": {
      "type": "string",
      "description": "The raw email headers, pasted in full"
    }
  },
  "required": [
    "headers"
  ]
}
🟢get_domain_health(domain)

One combined health report for a domain: SPF, DKIM (common selectors), DMARC, MX and blacklist status, with an overall score out of 100, the top problems, and the recommended fix order.

Input Schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Domain to check, e.g. example.com"
    }
  },
  "required": [
    "domain"
  ]
}
🟢analyze_dmarc_report(report_xml)

Explain a DMARC aggregate report in plain English: paste the report XML (the files sent to your rua address; several reports pasted together also work). Returns the reporting organisation and domain, total and passing message counts, a per-source breakdown (source IP, messages, SPF/DKIM verdicts, disposition) labelled as a legitimate sender, a forwarding / mailing-list pattern, or failing-and-suspicious — plus the top problems in fix order.

Input Schema

{
  "type": "object",
  "properties": {
    "report_xml": {
      "type": "string",
      "description": "The DMARC aggregate report XML in full (unzipped). Several reports pasted back to back are combined."
    }
  },
  "required": [
    "report_xml"
  ]
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded10 tools