IA-QA — 152 QA & Dev Tools for AI Agents

web_security_audit

Read-only

Run a comprehensive web security audit combining headers, SSL, CORS, and cookies checks — then use an LLM to produce a prioritised remediation plan. Orchestrates security_headers_check + ssl_certificate_check + cors_test + cookie_security_audit in parallel, merges all findings, then asks an AI model to: (1) rank vulnerabilities by real-world exploitability, (2) generate a remediation roadmap, (3) produce fix code snippets for the detected stack. Returns both raw audit data and the AI analysis. Use this as a one-click security posture assessment.

Input Schema

Name	Required	Description
`url`	Yes	Full URL to audit (e.g. https://example.com)
`model`	No	LLM model for AI analysis (default: "openai/gpt-oss-20b"). Set to "none" to skip AI analysis.
`api_key`	No	Your Groq or HuggingFace API key. Required to enable AI analysis.

Output Schema

Name	Required	Description	Default
`fix`	No
`key`	No
`url`	No
`name`	No
`weak`	No
`grade`	No
`score`	No
`tests`	No
`value`	No
`header`	No
`issues`	No
`secure`	No
`weight`	No
`cookies`	No
`details`	No
`message`	No
`missing`	No
`httpOnly`	No
`sameSite`	No
`risk_level`	No
`weak_count`	No
`cookies_found`	No
`missing_count`	No
`overall_grade`	No
`origins_tested`	No
`total_findings`	No
`headers_checked`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 31, 2026

addedInput schema / examples

Added value: +[
+  {
+    "model": "none",
+    "url": "https://www.ia-qa.com"
+  }
+]

Changed1 schema field changedAug 20, 2026

changedInput schema / properties / model / description

Previous value: -"LLM model for AI analysis (default: \"qwen/qwen3-32b\"). Set to \"none\" to skip AI analysis."New value: +"LLM model for AI analysis (default: \"openai/gpt-oss-20b\"). Set to \"none\" to skip AI analysis."

Changed1 schema field changedJun 21, 2026

addedOutput schema / properties

Added value: +{
+  "cookies": {
+    "type": "array"
+  },
+  "cookies_found": {
+    "type": "number"
+  },
+  "details": {},
+  "fix": {},
+  "grade": {},
+  "header": {},
+  "headers_checked": {
+    "type": "number"
+  },
+  "httpOnly": {},
+  "issues": {},
+  "key": {},
+  "message": {
+    "type": "string"
+  },
+  "missing": {},
+  "missing_count": {
+    "type": "number"
+  },
+  "name": {},
+  "origins_tested": {
+    "type": "number"
+  },
+  "overall_grade": {},
+  "risk_level": {},
+  "sameSite": {},
+  "score": {},
+  "secure": {},
+  "tests": {},
+  "total_findings": {
+    "type": "number"
+  },
+  "url": {},
+  "value": {},
+  "weak": {},
+  "weak_count": {
+    "type": "number"
+  },
+  "weight": {}
+}

Changed1 schema field changedJun 11, 2026

addedInput schema / properties / api_key

Added value: +{
+  "description": "Your Groq or HuggingFace API key. Required to enable AI analysis.",
+  "type": "string"
+}

Changed1 schema field changedJun 10, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

First observedMay 26, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already flag readOnly/openWorld/destructive=false, but the description adds behavior beyond them: parallel fan-out, result merging, an external LLM step, and the requirement for a Groq/HuggingFace API key. It also discloses that AI analysis can be skipped via model='none'. It doesn't mention cost/latency of the external API call or the non-determinism implied by idempotentHint=false, leaving minor gaps.

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?

Purpose is front-loaded in the first clause, followed by orchestration detail and the AI steps; nearly every sentence carries information. The numbered AI-step list and 'Returns both raw audit data and the AI analysis' are slightly over-detailed for a definition but still earn their place.

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

Completeness5/5

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

Output schema exists, annotations cover the safety profile, and all three params are documented. The description additionally explains the orchestration pipeline, the external API dependency, the skip option, and the return composition — everything an agent needs to invoke it correctly is present.

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?

Schema description coverage is 100%, so the schema already documents url, model (including 'none' to skip), and api_key. The description's mentions of 'asks an AI model' and the fix-snippet generation add a little rationale for the model/api_key params but no syntax or constraints beyond the schema. Baseline 3 applies.

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 ('Run a comprehensive web security audit') and enumerates the concrete checks it performs (headers, SSL, CORS, cookies). It explicitly differentiates from siblings by naming the four tools it orchestrates, so an agent can distinguish this aggregate tool from the individual checks without opening a 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?

The closing line 'Use this as a one-click security posture assessment' gives clear usage context, and naming the component tools implies the alternative (call them individually). It does not explicitly state when *not* to use this heavier orchestration versus a single cheap check, so not a full 5.

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

All IA-QA — 152 QA & Dev Tools for AI Agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.