- What it does
- Grade a page's security headers from pasted header text: HSTS, CSP basics, nosniff, framing, Referrer-Policy and Permissions-Policy, read as browsers read them, against the dated OWASP list, with a signed record.
- Who it is for
- Agents and their builders.
- Start in one step
- Ask your agent to call
security_headers_checkat llpro.ai/mcp (free, no sign-up). This page explains the tool; it has no form to run it. - What to expect
- Testing: open to try. Free
New to this? Start here.
What it does
Security Headers Check is for agents and developers that ship or review websites and need a fast, exact read of the security headers (with the reason for each gap) without sending a scanner at the site. Grade a web response's security headers from header text you paste (nothing is fetched). Six checks, each read the way its standard says a browser reads it: Strict-Transport-Security (RFC 6797), Content-Security-Policy basics (CSP Level 3: script sources, 'unsafe-inline', wildcards, 'unsafe-eval'), X-Content-Type-Options, framing (CSP frame-ancestors, else X-Frame-Options), Referrer-Policy and Permissions-Policy, against the OWASP Secure Headers Project list (dated 2026-10-18). Get back pass, weak, fail or missing per check with the reason, a letter grade, headers that leak server details, and the other OWASP-list headers not set. It is one of the developer department tools LLPRO builds for the work agents do across business software (Cloudflare, Vercel, Netlify, Nginx, Aws). Every answer carries the written rule it used, what it does not do, its sources with dates, and an Ed25519 signature you can check against the key below.
- Who it is for
- Agents and developers that ship or review websites and need a fast, exact read of the security headers (with the reason for each gap) without sending a scanner at the site.
- Price
- Free, no sign-up: 120 calls an hour per address and 3,000 an hour across all callers. Paid calls are planned and not charging.
- Limits
- Up to 30,000 bytes per call; larger requests are refused, never cut. Unknown fields are refused with the list of accepted ones. Nothing you send is stored by the tool; no model and no network are used. Does not fetch the page, follow redirects or see headers set by a meta tag; grade the final response of the HTML page (APIs and images need fewer of these). Does not check every CSP directive (style-src, connect-src, img-src, script-src-elem and -attr, trusted types) or whether your nonces are random, and does not test the site for XSS or clickjacking. Does not check HSTS preload list membership (hstspreload.org adds its own rules, such as the preload token and the redirect setup), cookies or CORS. The letter grade is LLPRO's own scale over these six checks, not an OWASP grade. Not a security audit.
For developers: try it
POST https://llpro.ai/mcp
{"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {"name": "security_headers_check", "arguments": {"headers": "HTTP/2 200\r\nStrict-Transport-Security: max-age=63072000; includeSubDomains\r\nContent-Security-Policy: default-src 'self'; object-src 'none'; base-uri 'self'; form-action 'self'; frame-ancestors 'none'\r\nX-Content-Type-Options: nosniff\r\nReferrer-Policy: no-referrer\r\nPermissions-Policy: camera=(), geolocation=(self), microphone=()"}}}For agents
Tool security_headers_check on https://llpro.ai/mcp and in the tools list. Signed answers are checked with the public key below (signer llpro1:67lk5oufixle4g3z75aycgupxy): an Ed25519 signature over the observation as canonical JSON (sorted keys, no spaces).
Public key (base64): BKJYavPbuqcVpgy4zhYsAjyaTm2MFGVc2Kb0yclcfoc=
For agents that search MCP registries for security headers, Content-Security-Policy, HSTS tools (listed in MCP registries, served by the Campus gateway: MCP, agent-to-agent and REST). One fixed, written rule per call, a signed record, no account needed.
Next
- Connect your agent: Use this and the other LLPRO tools from your own agent.
- Get your agent: No agent yet? Get one that asks first.
- Hand the whole job to the Hub: Security headers are one step of checking a website. Tell the Hub the whole job; it routes you to the right signed tools (HTTP cache freshness, robots.txt check, llms.txt check).
For agents: this page as Markdown · JSON · llms.txt · MCP endpoint llpro.ai/mcp · agent card