Skip to main content
Glama

http_headers_audit

Audit HTTP security headers and cookie flags to detect misconfigurations and return a 0–100 score with grade for prioritizing fixes.

Instructions

Audit HTTP security headers and cookie flags; returns a score (0-100) and grade.

Checks HSTS, CSP, X-Frame-Options/CSP frame-ancestors, nosniff, Referrer-Policy, Permissions-Policy and COOP/CORP. Also flags version/tech disclosure.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "http_headers_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations at all, the description carries the full burden. It does well on scope and output shape (numeric score plus letter grade, plus a separate disclosure flag), but says nothing about whether it performs live network requests, how it handles redirects/TLS errors, timeouts, or rate limits — relevant for a tool that must hit a remote host.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short blocks, front-loaded with the purpose and output, then a compact list of what is inspected. No filler, no restating of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-URL, read-only audit with no output schema, the description covers what is checked and what is returned, which is enough to call it correctly. The remaining gap is URL format and failure behavior, which is minor but not negligible given 0% schema coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter (url) with 0% schema description coverage, so the description should compensate and does not — it never specifies whether the URL must include a scheme, whether a path matters, or whether redirects to https are followed. The listed checks implicitly scope it to a single URL, which is a small assist.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Audit HTTP security headers and cookie flags') and names the concrete deliverables (score 0-100 and grade). The enumerated checks (HSTS, CSP, X-Frame-Options, nosniff, Referrer-Policy, Permissions-Policy, COOP/CORP, version disclosure) make it unmistakable against siblings like http_fetch or browser_crawl.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the subject matter — an agent can infer this is the header-hardening check rather than a fetch tool — but there is no explicit when/when-not guidance and no named alternatives. Nothing tells the agent whether to run this before or after fetching the page, or what to do with a failing grade.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.