
ExposureGuard
- Updated April 18, 2026
- ExposureGuard/exposureguard-mcp
io.github.ExposureGuard/exposureguard-mcp is a MCP server that scans domains for agents, assigns A–F grades across eight checks, and supplies fix snippets.
About
ExposureGuard MCP turns domain security review into agent-callable tools: scan a hostname, get an A–F grade, see results from eight checks, and receive fix snippets the agent can apply or paste into infra repos. developers shipping SaaS or marketing sites often skip manual scanner tabs; this server keeps grading inside Claude Code or Cursor right before launch. It is phase-specific to Ship security—not continuous production monitoring unless you wire recurring scans yourself. Install the PyPI distribution with stdio transport, point it at domains you own or are authorized to test, and treat output as guidance alongside your own threat model. Intermediate complexity reflects interpreting DNS, TLS, and header findings correctly. Pair it with your deploy checklist rather than as a substitute for full penetration testing.
- A–F letter grades summarizing domain security posture for quick agent decisions
- Eight distinct security checks per scan (per server description)
- Fix snippets returned with findings so the agent can patch headers, DNS, or config
- PyPI package exposureguard-mcp (v1.0.2) with stdio MCP transport
- Built for AI agents—ExposureGuard branding in MCP registry metadata
ExposureGuard by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add exposureguard-mcp -- uvx exposureguard-mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | exposureguard-mcp |
|---|---|
| Transport | STDIO |
| Auth | None |
| Last updated | April 18, 2026 |
| Repository | ExposureGuard/exposureguard-mcp ↗ |
What it does
Let your agent grade a domain’s exposure with A–F scores, run eight security checks, and return fix snippets before you ship or point DNS at production.
Who is it for?
Best when you're validating production or staging hostnames from the same session that edits Terraform, DNS, or app security headers.
Skip if: Deep in-app OWASP testing, internal VPC audits, or compliance programs that need certified assessors only.
What you get
Your agent returns a graded domain report with eight check results and actionable fix snippets you can implement before go-live.
- A–F domain security grade from agent-invoked scan
- Structured output covering eight security checks
- Fix snippets the agent can turn into PRs or infra edits
By the numbers
- 8 security checks per domain scan (stated in description)
- A–F grading scale
- Server version 1.0.2
README.md
ExposureGuard MCP Server
An MCP (Model Context Protocol) server that connects AI assistants to the ExposureGuard domain security scanning API.
Tools
| Tool | Description |
|---|---|
scan_domain |
Full security scan — 8 checks, A-F grade, score, findings, report URL (~8s) |
get_grade |
Cached grade lookup (up to 24h old) — fast, no new scan triggered |
get_remediation |
Copy-paste fix snippets for all failing checks |
get_dependencies |
Third-party scripts/resources loaded by the domain |
Setup
1. Get an API Key
Sign up at getexposureguard.com and grab your API key from the dashboard.
2. Install
# Option A: pip install (recommended)
pip install -e /path/to/exposureguard-mcp
# Option B: just install deps
pip install mcp httpx
3. Configure Your AI Client
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"exposureguard": {
"command": "python",
"args": ["-m", "exposureguard_mcp.server"],
"env": {
"EXPOSUREGUARD_API_KEY": "your-api-key-here"
}
}
}
}
If you installed as a package, you can also use:
{
"mcpServers": {
"exposureguard": {
"command": "exposureguard-mcp",
"env": {
"EXPOSUREGUARD_API_KEY": "your-api-key-here"
}
}
}
}
Cursor
Edit .cursor/mcp.json in your project root (or globally at ~/.cursor/mcp.json):
{
"mcpServers": {
"exposureguard": {
"command": "python",
"args": ["-m", "exposureguard_mcp.server"],
"env": {
"EXPOSUREGUARD_API_KEY": "your-api-key-here"
}
}
}
}
Windsurf
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"exposureguard": {
"command": "python",
"args": ["-m", "exposureguard_mcp.server"],
"env": {
"EXPOSUREGUARD_API_KEY": "your-api-key-here"
}
}
}
}
VS Code (Copilot)
Edit .vscode/mcp.json in your project:
{
"servers": {
"exposureguard": {
"type": "stdio",
"command": "python",
"args": ["-m", "exposureguard_mcp.server"],
"env": {
"EXPOSUREGUARD_API_KEY": "your-api-key-here"
}
}
}
}
4. Usage Examples
Once connected, ask your AI assistant:
- "Scan example.com for security issues"
- "What's the security grade for cloudflare.com?"
- "Show me how to fix the security issues on my-site.com"
- "What third-party scripts does shopify.com load?"
Running Standalone
export EXPOSUREGUARD_API_KEY=your-api-key-here
python -m exposureguard_mcp.server
The server communicates over stdio using the MCP protocol — it's designed to be launched by an MCP client, not used interactively.
Rate Limits
Rate limits depend on your ExposureGuard plan. If you hit a 429 response, the server will return a message suggesting you upgrade at getexposureguard.com/pricing.
Publishing
PyPI
pip install build twine
python -m build
twine upload dist/*
Then users install with: pip install exposureguard-mcp
npm
npm publish
Then users install with: npx exposureguard-mcp
License
MIT
Recommended MCP Servers
How it compares
Domain exposure scanner MCP—not a secrets vault and not a generic code linter.
FAQ
Who is io.github.ExposureGuard/exposureguard-mcp for?
Developers and agents that need quick, structured domain security grades and fixes before launch.
When should I use io.github.ExposureGuard/exposureguard-mcp?
In Ship security passes on public domains, after DNS cutover planning, or when an agent is hardening a new marketing or app URL.
How do I add io.github.ExposureGuard/exposureguard-mcp to my agent?
Install exposureguard-mcp from PyPI, add a stdio MCP server block in Claude or Cursor per ExposureGuard/exposureguard-mcp repo instructions, then invoke scan tools on authorized domains.