@dmarc-examiner/mcp

MCP serverFiles & storage

Your AI can read the DMARC reports for your own domain, covering both aggregate and forensic reports. That means you can ask it to show which sources have been sending email as your domain, whether their messages align with your settings, and where alerts show up in the reports. Findings can be exported as CSV.

Available today. Use it from your connected AI after setup.

Add the app and ask your AI to read the DMARC reports for your domain. From there, request a summary, drill into a specific source, or get a CSV export of the findings.

Then ask your AI: use @dmarc-examiner/mcp to list domains

What your AI can do with it

  • Read your DMARC aggregate reports
  • Go through forensic DMARC reports
  • Show which sources are sending email as your domain
  • Check whether messages align with your DMARC settings
  • Spot alerts flagged in your reports
  • Export report data as CSV

From the project's README

As published by dmarc-examiner/mcp in README.md.

Official MCP (Model Context Protocol) server for DMARC Examiner. Query your DMARC monitoring data from AI assistants like Claude Desktop, Claude Code, and Cursor.

Why

DMARC aggregate reports arrive as compressed XML, one file per receiver per day. Reading them means either opening a dashboard or parsing XML by hand.

This server puts that data behind an MCP connection, so you can ask questions instead:

Which sending sources failed DMARC alignment last week?

Show me the domains where SPF passes but DKIM does not.

Export the report for example.com as CSV.

DMARC Examiner is a DMARC monitoring service with a free tier — you need an account to use this server, but not a paid one.

Quick Setup

Option 1: Remote URL (Recommended)

Most MCP clients support remote HTTP servers directly. Add this to your MCP configuration:

{
  "mcpServers": {
    "dmarc-examiner": {
      "url": "https://mcp.dmarc-examiner.com/mcp"
    }
  }
}

Option 2: npx (for clients without remote HTTP support)

{
  "mcpServers": {
    "dmarc-examiner": {
      "command": "npx",
      "args": ["-y", "@dmarc-examiner/mcp"]
    }
  }
}

Configuration by Client

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "dmarc-examiner": {
      "url": "https://mcp.dmarc-examiner.com/mcp"
    }
  }
}

Claude Code

claude mcp add dmarc-examiner --transport http https://mcp.dmarc-examiner.com/mcp

Cursor

Add to your Cursor MCP settings:

{
  "mcpServers": {
    "dmarc-examiner": {
      "url": "https://mcp.dmarc-examiner.com/mcp"
    }
  }
}

Authorization

Adding the server does not require authorizing. It starts immediately and answers initialize, tools/list and ping without credentials, so your client can list all 21 tools straight away.

A browser opens the first time you call a tool that touches your data. You'll need to:

  1. Log in to your DMARC Examiner account
  2. Select which organization to connect
  3. Approve the requested permissions (scopes)

The call you made is then replayed automatically, so it completes rather than failing.

With Option 1 the MCP client runs this flow itself. With Option 2 the package does it: it registers as an OAuth client, opens your browser, and stores the resulting tokens in ~/.dmarc-examiner/mcp-credentials.json with 0600 permissions. The refresh token is reused on later runs, so the browser step happens once.

Why it works this way. Authorizing on startup is the obvious design and it breaks every automated client: directory checks, scanners and CI have no browser to open, so the server appears to hang and the check times out. We wrote up the failure and the fix, with logs, in Your Remote MCP Server Will Fail Every Directory Check.

You can also drive it directly:

npx -y @dmarc-examiner/mcp login    # authorize now, outside your MCP client
npx -y @dmarc-examiner/mcp logout   # forget the stored credentials

Set DMARC_EXAMINER_MCP_URL to point the package at a different endpoint.

Available Tools

Domains

ToolDescriptionScope
list_domainsList all monitored domains in your organizationdomains:read
get_domainGet details of a specific domaindomains:read
check_dmarcInspect the public DMARC record at _dmarc.<domain>. Works on any domain, not only your owndomains:read
create_domainAdd a domain. Returns the reporting email and DMARC record to publish in DNSdomains:manage
verify_domainRe-check DNS to confirm the DMARC record carries your reporting addressdomains:manage
delete_domainRemove a domain from monitoring. Soft delete — historical reports remaindomains:manage

Aggregate reports (RUA)

ToolDescriptionScope
list_reportsList DMARC reports with filteringreports:read
get_reportGet a detailed report with recordsreports:read
get_report_statisticsReport statistics by country and ASNreports:read
export_report_csvExport a report as CSVreports:export

Forensic reports (RUF)

Requires the Pro plan or above; these return 403 otherwise.

ToolDescriptionScope
list_forensic_reportsList RUF reports with filtering and paginationforensic:read
get_forensic_reportFull detail of a forensic report, including the failed message envelopeforensic:read
get_forensic_reports_statisticsCounters by failure type, delivery result, source IP with geolocation, and domainforensic:read
get_forensic_reports_summaryForensic activity over the last 7 daysforensic:read

Alerts

ToolDescriptionScope
list_alertsList security alertsalerts:read
dismiss_alertDismiss an alertalerts:manage

Webhooks

Requires the Pro plan or above; these return 403 otherwise.

ToolDescriptionScope
list_webhooksList configured webhook endpointswebhooks:read
create_webhookCreate an endpoint. The URL must be HTTPSwebhooks:manage
update_webhookUpdate the URL, name or active state of an endpointwebhooks:manage
delete_webhookDelete an endpoint permanentlywebhooks:manage
test_webhookSend a webhook.test event and return the delivery statuswebhooks:manage

Scopes

ScopeDescription
domains:readView monitored domains
domains:manageAdd, verify and remove domains
reports:readView reports and statistics
reports:exportExport reports to CSV
forensic:readView forensic (RUF) reports
alerts:readView alerts
alerts:manageManage alerts (dismiss)
webhooks:readView webhook endpoints
webhooks:manageCreate, update, delete and test webhooks

Documentation

For detailed documentation, visit: https://dmarc-examiner.com/docs/settings/mcp-integration?utm_source=github&utm_medium=content&utm_campaign=mcp-repo

Support

License

MIT — see LICENSE.

Tools it offers (21)

What this server listed when ahel dialed its public endpoint in Sep 2026, with no key and no account of yours. The names are the server’s own.

  • list_domains
  • get_domain
  • check_dmarc
  • create_domain
  • verify_domain
  • delete_domain
  • list_reports
  • get_report
  • get_report_statistics
  • export_report_csv
  • list_alerts
  • dismiss_alert
  • list_forensic_reports
  • get_forensic_report
  • get_forensic_reports_statistics
  • get_forensic_reports_summary
  • list_webhooks
  • create_webhook
  • update_webhook
  • delete_webhook
  • test_webhook

Signals

Last commit
Aug 2026
Advanced
Delivery
mcp MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
Catalog kind
mcp-server
Gateway key
io-github-dmarc-examiner-mcp
Source
github.com/dmarc-examiner/mcp
Hosted endpoint
https://mcp.dmarc-examiner.com/mcp