Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/modelcontextprotocol-security/mcpserver-audit/claude-mdgit clone --depth 1 https://github.com/ModelContextProtocol-Security/mcpserver-auditWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01502 | $0.01502 |
| Opus 5 | $0.00751 | $0.00751 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
mcpserver-audit 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Purpose
This is mcpserver-audit, a security auditing tool for Model Context Protocol (MCP) servers and Claude Desktop Extensions. It serves as an expert security tutor that teaches users how to audit MCP server source code for vulnerabilities using AIVSS (AI Vulnerability Scoring System) scoring.
Key Role: Find security vulnerabilities in existing code (not fix them - that's handled by mcpserver-builder)
Architecture Overview
This is a prompt-driven security education system built around three core components:
1. Security Assessment Prompts (prompts/)
- Conversational AI instructions that implement expert security tutoring
- Use Socratic method to teach vulnerability identification rather than just providing answers
- Each prompt targets specific security assessment scenarios:
main-prompt.md: Core security tutor personasecurity-assessment.md: Comprehensive vulnerability scanning workflowtargeted-evaluation.md: Focused security assessment of known servers
- Usage pattern:
read prompts/[file].md and [security assessment action]
2. Modular Security Checks (checks/)
- Technical vulnerability detection procedures with both automated and manual steps
- Each check targets specific CWE categories with AIVSS scoring
- Include concrete detection scripts, risk assessment, and remediation guidance
- Format: Obsidian-style markdown with CWE mappings and vulnerability-db integration
- Current coverage (~12 checks): application-level (credential management, network port binding, dynamic content execution, advanced obfuscation/evasion, HTTP client resilience) and infrastructure/supply-chain (Docker, Docker Compose, Kubernetes, CI secrets, Python auth via Semgrep). Gaps remain — see
GAPS.md.
3. Knowledge Frameworks (research/, resources/, tools/)
- Supporting materials for threat modeling, risk assessment, and compliance mapping
- Templates and checklists for systematic security evaluation
- Placeholder for future MCP tool implementations
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.
- 2d ago First seen · 139 lines · 1,502 tokens per session scan A 64b06f0070a5
mcpserver-audit CLAUDE.md is an instructions file published in the GitHub repository ModelContextProtocol-Security/mcpserver-audit (22 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,502 tokens to every session, about $0.0075 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 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.