qualys-pci-mcp: Instructions file for Claude Code

CLAUDE.md

qualys-pci-mcp CLAUDE.md is an instructions file for Claude Code from RobotDisco/qualys-pci-mcp. It costs 1,456 tokens per session, scanned A, original, Apache-2.0.

Project instructions for a read-only connection to Qualys PCI Merchant API, a service used to manage payment-card security compliance. They define safety rules for requests, credentials, logging, and API behaviour.

In plain words
What is it for?
Use them when developing or changing the Qualys PCI MCP server, especially when adding an endpoint, handling authentication, or checking where code and commands belong.
Why use it?
They prevent accidental changes to compliance data and avoid exposing credentials or corrupting the agent’s communication channel. They also keep returned data faithful to what Qualys provides.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is RobotDisco/qualys-pci-mcp's own configuration. It tells Claude Code how to work on qualys-pci-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything qualys-pci-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RobotDisco/qualys-pci-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/RobotDisco/qualys-pci-mcp/trunk/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/RobotDisco/qualys-pci-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for qualys-pci-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/robotdisco/qualys-pci-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/robotdisco/qualys-pci-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/robotdisco/qualys-pci-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/robotdisco/qualys-pci-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for qualys-pci-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/robotdisco/qualys-pci-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/robotdisco/qualys-pci-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,456 This file is loaded in full into every session.
When invoked 1,456 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01456 $0.01456
Opus 5 $0.00728 $0.00728
Sonnet 5 $0.00291 $0.00291
Haiku 4.5 $0.00146 $0.00146

Measured 8d ago against content hash 3877dac3d808, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

qualys-pci-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

qualys-pci-mcp

Read-only MCP server over the Qualys PCI Merchant API (https://pci-api.qualys.com/pci/).

Purpose: reduce the manual effort of weekly PCI compliance obligations.

Non-negotiable invariants

  1. Strictly GET. No POST/PUT/DELETE against business endpoints — no report generation, no scan launches, no false-positive submissions. → docs/adr/0002-read-only-strictly-get.md
  2. stdout is the JSON-RPC channel. Never print(). All logging goes to stderr. A stray write to stdout corrupts the MCP stream and the failure looks unrelated.
  3. No invented semantics. Return Qualys fields as Qualys sends them. In particular there is no live/not-live host flag in this API — do not derive one. → docs/adr/0004-no-derived-liveness.md
  4. Never retry a 401. Fail closed immediately. Retrying a bad password locks the Qualys account needed for quarterly audits.
  5. Credentials are SecretStr and never appear in logs, errors, or URLs (no secrets in query strings, ever).
  6. Only client.py may import httpx — a ruff banned-api rule bans it everywhere and allowlists that one module (plus tests). If anything else needs HTTP, a boundary is wrong.
  7. Never invent an endpoint path. Only paths marked verified in the reference (see the table below) are known to exist. Confirm an unverified one against live docs first, then record it. Every URL string lives in endpoints.py and nowhere else.
  8. No test touches the live API. Everything is respx-mocked. Note the corollary: fixtures were written from Qualys's documentation, and the documentation has been wrong three times — so a green suite is not evidence the shape is right. Confirm with scripts/live-check.py.
  9. Never ship a filter that might be ignored. Qualys discards unrecognised parameter names and answers HTTP 200 with the unfiltered set, so a wrong name silently returns everything while the caller believes it narrowed. Verify a filter narrows before exposing it, or raise UnsupportedFilterError.
  10. Settings.from_env() is the only way to construct Settings. Calling Settings() fails mypy and skips the misspelled-variable check.
  11. Every raised error derives from QualysPCIError. Wrap foreign exceptions — a pydantic.ValidationError is a ValueError, so unwrapped it slips past every caller's except QualysPCIError and reaches the MCP client as a raw traceback.
  12. Model fields are snake_case; the wire is camelCase. to_camel bridges them, so add fields in snake_case and let the alias generator do the mapping.

Read the full file on GitHub · 104 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 104 lines · 1,456 tokens per session scan A 3877dac3d808

Subscribe to this mod's changes

qualys-pci-mcp CLAUDE.md is an instructions file published in the GitHub repository RobotDisco/qualys-pci-mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,456 tokens to every session, about $0.0073 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens