HeaderGuard
by headerguard.mike-tusa.workers.dev · remote · no sign-in to list tools · v0.4.0 · published by dev.workers.mike-tusa.headerguard
Scan a website's HTTP security headers (HSTS, CSP, framing, COOP/CORP, cookies). Score + fixes.
1 tool: 1 change things.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things1Claude Code: ask: see these tools
- Only reads0Claude Code: allow
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http headerguard https://headerguard.mike-tusa.workers.dev/mcpTools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
1 tool
Changes things 1Claude Code: ask
scan_headersScan the HTTP security headers of a public website.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Scan the HTTP security headers of a public website. Returns a 0–100 score and A+–F grade (HTTPS 10, HSTS 15, CSP 25, framing 10, X-Content-Type-Options 10, Referrer-Policy 10, Permissions-Policy 5, COOP 5, CORP 5, cookies 5, minus up to 5 for version-leak headers; without HTTPS the score is capped at 39), each header's status and notes, recommended fix headers, and a link to the full report with copy-paste snippets for nginx, Apache, Cloudflare, Netlify, Vercel and Express. Read-only: it sends ordinary GET requests to the site (following up to 10 redirects, each safety-checked) and never reads page bodies. Same engine and scoring as the HeaderGuard JSON API (GET /api/scan).
Annotations the server declares
- title: Scan security headers
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Install
Pinned to version 0.4.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http headerguard https://headerguard.mike-tusa.workers.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__headerguard__scan_headers"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as headerguard. Review it before you use it.