mcpField
D
domainintel-mcp

domainintel-mcp

Local
github.com/Bishop81Security0Updated 14w ago
Repository

About domainintel-mcp

domainintel-mcp is an MCP server for agents and security teams that analyzes domains and raw email headers. It combines registration, DNS, certificate, header, reputation, and subdomain checks, with an overall security grade.

Key features

  1. 01WHOIS registration details
  2. 02DNS records and SPF/DMARC checks
  3. 03SSL/TLS certificate analysis
  4. 04HTTP security-header scoring
  5. 05Domain reputation and subdomain discovery
  6. 06Full domain report and email-header analysis

Use cases

  1. 01Review a domain’s security posture
  2. 02Check DNS configuration and email authentication
  3. 03Find subdomains from certificate logs and probes
  4. 04Inspect email delivery paths and spoofing indicators

MCP support

Exposes domain and email-header analysis tools to MCP clients over stdio.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "bishop81-domainintel": {
      "command": "npx",
      "args": [
        "-y",
        "@domainintel/mcp"
      ]
    }
  }
}
Run commandnpx -y @domainintel/mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@domainintel/mcp1.0.2

Tools

7

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
domainstringYesDomain name to analyze, e.g. "example.com" (protocol, www. and paths are stripped automatically)

Details

From the project README

@domainintel/mcp

An MCP server that gives AI agents live domain intelligence: WHOIS, DNS, SSL/TLS, HTTP security headers, reputation, and subdomain discovery for any domain. It is the same analysis engine that powers DomainIntel.app.

Tools

ToolReturns
whois_lookupRegistrar, creation/expiry/updated dates, registrant country, privacy status, nameservers
dns_recordsA, AAAA, MX, TXT, NS, CNAME, CAA records + SPF/DMARC presence + misconfiguration warnings
ssl_certificateValidity, issuer, expiration, days remaining, protocol, warnings
security_headersHSTS, CSP, X-Frame-Options and others, scored with recommendations
domain_reputationDNSBL / Spamhaus blocklist checks and a reputation score
subdomain_discoverySubdomains via Certificate Transparency logs and common-prefix probing
full_domain_reportEvery analyzer at once plus an overall A+ to F security score
analyze_email_headersParses a raw email header block: SPF/DKIM/DMARC results, the Received delivery path with timing, key envelope fields, and a From-vs-Return-Path spoofing flag

Every tool except analyze_email_headers takes a single domain argument; protocol, www., and paths are stripped automatically. analyze_email_headers takes a headers string (a pasted raw header block) instead.

Requirements

  • Node.js 18 or newer

Install

Claude Code
claude mcp add domainintel -- npx -y @domainintel/mcp
Claude Desktop

Add to claude_desktop_config.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "domainintel": {
      "command": "npx",
      "args": ["-y", "@domainintel/mcp"]
    }
  }
}
Any other MCP client

The server speaks MCP over stdio:

npx -y @domainintel/mcp

Example prompts

  • "Run a full domain report on stripe.com"
  • "What are the MX records for github.com, and does it have DMARC?"
  • "Is the SSL certificate for example.org close to expiring?"

Development

Run from source (no build needed):

git clone <repo> && cd domainintel.app
npm install
npm run mcp        # node mcp/server.mjs

Building & publishing

The published package is a single self-contained bundle (the analyzers and all JS dependencies are bundled with esbuild; Node built-ins resolve at runtime).

npm run build:mcp          # from repo root -> mcp/dist/server.mjs
cd mcp && npm publish       # prepublishOnly rebuilds the bundle

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.