Skip to main content
Glama

HubVibe: Pay-per-Call Agent Tools: Web Search, Email Verify, KYC Screening, Stocks, Crypto, News

Security header audit

audit_security
Read-onlyIdempotent

Security headers check for a website: audits HTTPS, HSTS, Content- Security-Policy (CSP), X-Content-Type-Options, X-Frame-Options / clickjacking protection, Referrer-Policy and CORS from the real HTTP response of any live URL. Findings with severity for what is missing. Header posture only, not a penetration test. $0.05 per call.

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": "audit_security"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
languageNo

Output Schema

NameRequiredDescriptionDefault
passYes
statusNo
findingsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • removedInput schema / properties / language / description
      Removed value: -"Optional BCP-47 language tag (en, ja, ko, pt-BR): the human-readable text of the findings is returned in this language; rule ids, severities, URLs and numbers are untouched. Default: English."
    • removedInput schema / properties / language / examples
      Removed value: -[
      -  "ja"
      -]
    • removedInput schema / properties / url / description
      Removed value: -"Live, fetchable http(s) URL to audit."
    • removedInput schema / properties / url / examples
      Removed value: -[
      -  "https://example.com"
      -]
    • removedInput schema / title
      Removed value: -"Live URL to audit"
  2. Changed6 schema fields changed
    • removedOutput schema / properties / findings / description
      Removed value: -"One entry per rule that did not pass. Empty when the check is clean."
    • removedOutput schema / properties / findings / items / properties
      Removed value: -{
      -  "detail": {
      -    "description": "What failed and where.",
      -    "type": "string"
      -  },
      -  "id": {
      -    "description": "Stable rule identifier.",
      -    "type": "string"
      -  },
      -  "severity": {
      -    "description": "Rule severity.",
      -    "type": "string"
      -  }
      -}
    • removedOutput schema / properties / findings / items / required
      Removed value: -[
      -  "id"
      -]
    • removedOutput schema / properties / findings / items / type
      Removed value: -"object"
    • removedOutput schema / properties / pass / description
      Removed value: -"Whether every rule in this dimension passed."
    • removedOutput schema / properties / status / description
      Removed value: -"Present only on a completed audit."
  3. Changed1 schema field changed
    • addedInput schema / properties / language
      Added value: +{
      +  "description": "Optional BCP-47 language tag (en, ja, ko, pt-BR): the human-readable text of the findings is returned in this language; rule ids, severities, URLs and numbers are untouched. Default: English.",
      +  "examples": [
      +    "ja"
      +  ],
      +  "maxLength": 35,
      +  "pattern": "^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$",
      +  "type": "string"
      +}
  4. Changed6 schema fields changed
    • addedInput schema / $schema
      Added value: +"https://json-schema.org/draft/2020-12/schema"
    • changedInput schema / properties / url / description
      Previous value: -"Live URL to audit"New value: +"Live, fetchable http(s) URL to audit."
    • addedInput schema / properties / url / examples
      Added value: +[
      +  "https://example.com"
      +]
    • addedInput schema / properties / url / format
      Added value: +"uri"
    • addedInput schema / title
      Added value: +"Live URL to audit"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "https://json-schema.org/draft/2020-12/schema",
      +  "properties": {
      +    "findings": {
      +      "description": "One entry per rule that did not pass. Empty when the check is clean.",
      +      "items": {
      +        "properties": {
      +          "detail": {
      +            "description": "What failed and where.",
      +            "type": "string"
      +          },
      +          "id": {
      +            "description": "Stable rule identifier.",
      +            "type": "string"
      +          },
      +          "severity": {
      +            "description": "Rule severity.",
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "id"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "pass": {
      +      "description": "Whether every rule in this dimension passed.",
      +      "type": "boolean"
      +    },
      +    "status": {
      +      "const": "ok",
      +      "description": "Present only on a completed audit.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "pass"
      +  ],
      +  "type": "object"
      +}
  5. First observed

TDQS

A3.9/5.0
Behavior4/5

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

The annotations already declare read-only, idempotent and open-world behavior, so the description is not carrying the safety burden. It still adds genuinely useful context beyond them: output shape (findings with severity for what is missing) and cost ($0.05 per call), which matters for a paid network-dependent call. It does not mention rate limits, auth needs, or that no live endpoint means no findings.

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

Conciseness4/5

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

One front-loaded sentence names the subject and the checks, followed by three short clauses covering severity output, scope limits and pricing. Slightly dense header list, but there is no filler and every clause adds information.

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

Completeness3/5

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

With an output schema and full annotations available, most of the burden is covered, and the price/scope notes fill in the rest. The gap is the undocumented language parameter and the absence of any statement about what happens when a URL is unreachable, which is a real possibility for an open-world HTTP probe.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate and it largely does not. "Any live URL" weakly constrains the url parameter but gives no format or scheme guidance, and the language parameter is never mentioned at all, leaving an agent to guess its purpose.

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?

The description names a specific verb and resource ("Security headers check for a website") and enumerates exactly what is audited: HTTPS, HSTS, CSP, X-Content-Type-Options, X-Frame-Options/clickjacking, Referrer-Policy and CORS. This makes it trivially distinguishable from the seo, performance and wcag audits in the sibling set without opening any schema.

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

Usage Guidelines4/5

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

It states the operating condition ("from the real HTTP response of any live URL") and one explicit exclusion ("Header posture only, not a penetration test"). What is missing is any routing guidance toward the alternative lying in audit_bundle or the other per-domain audits when an agent wants a combined report.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.