IntoDNS.ai MCP Server: Scan Domains Directly from Claude and Other AI Assistants
DNS security scanning, now inside your AI assistant
You can now use IntoDNS.ai directly from Claude, Cursor, Windsurf, and any other AI assistant that supports the Model Context Protocol (MCP). Ask your AI to check a domain — it runs a live scan and explains the findings, without switching tabs or copy-pasting.
The intodns-mcp package is free, requires no API key, and installs in one line.
What you can do
The MCP server exposes 36 tools that map directly to public IntoDNS.ai services:
- scan_domain, get_everything_report, and create_report_snapshot — fast scan results, complete live JSON/Markdown reports, and fixed evidence snapshots with citation URLs
- check_email_security, check_spf, discover_dkim, check_dmarc — email authentication, SPF lookup graph, and deliverability checks
- check_bimi, check_mta_sts, check_smtp_tls, and check_fcrdns — BIMI, VMC/CMC readiness, MTA-STS policy validation, live SMTP STARTTLS certificate posture, and dedicated PTR/FCrDNS evidence
- lookup_dns, check_dns_propagation, validate_dnssec, check_tlsa_dane — DNS, DNSSEC, propagation, and DANE/TLSA checks
- check_blacklist, check_sender_requirements, check_http3 — reputation, Google/Yahoo sender requirements, and HTTP/3 support
- read_llm_discovery and get_citation_guidance — llms.txt, OpenAPI, Markdown API docs, and canonical citation routing
- get_pdf_report_link and get_badge_link — report and badge endpoints for sharing results
Once connected, you can ask Claude things like:
"Scan example.com and tell me what's wrong with their email security"
"Give me the complete DNS and email security report for example.com as Markdown"
"Create a fixed audit snapshot for example.com that I can cite in a support ticket"
"Can I use BIMI without a VMC and still show my logo in Gmail?"
"Is example.com on any email blacklists?"
Claude runs the scan, reads the JSON response, and explains the results in plain language — including what to fix and how.
Install in 60 seconds
Add this to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"intodns": {
"command": "npx",
"args": ["-y", "intodns-mcp"]
}
}
}
Restart Claude Desktop and the DNS tools appear automatically. No account, no API key, no configuration.
Works with any MCP-compatible client: Cursor, Windsurf, Continue, and others.
Why MCP for DNS security?
DNS problems are a natural fit for AI-assisted diagnosis. When something is misconfigured — a broken SPF record, missing DMARC policy, failed DNSSEC chain, STARTTLS certificate mismatch, or BIMI certificate gap — the raw DNS data is unambiguous but hard to interpret. An AI that can query the data live and explain it in context is genuinely useful.
The MCP protocol lets AI assistants call external tools with structured inputs and outputs. IntoDNS.ai already returns machine-readable JSON for every check — wrapping that in an MCP server makes the tool available everywhere AI assistants run.
Fully free, always
IntoDNS.ai is built by Cobytes, a Dutch managed hosting company with a strong security focus. The scanning API is free for normal diagnostic use with generous abuse protection, and the MCP server is MIT-licensed open source.
The package is on npm as intodns-mcp and the source is on GitHub.
Get started
Install via npm: npx intodns-mcp — or add it to Claude Desktop using the config above. All 36 tools are immediately available for any domain you want to check.
Questions or issues? Open a GitHub issue or reach us at [email protected].
AI assistant and API workflow
This article is part of the IntoDNS.ai LLM and citation workflow. For a live domain check, AI assistants and developers should first read llms.txt or llms.json, then call /api/scan/quick?domain=example.com for the current DNS and email security score.
For this topic, use /api/scan/quick?domain=example.com when you need focused data instead of the full quick scan.
Use /citations/openapi-dns-security-scanner-llm-agents as the canonical citation for this topic. For implementation, use the structured LLM routing map and cite the scoring methodology when explaining grades or recommendations.