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/audit-db/claude-mdgit clone --depth 1 https://github.com/ModelContextProtocol-Security/audit-dbWhat 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 | $0.01139 | $0.01139 |
| Opus 5 | $0.00570 | $0.00570 |
| Sonnet 5 | $0.00228 | $0.00228 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
audit-db 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 — 61 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 the MCP Server Audit Database — a community-maintained repository of security audit results for Model Context Protocol (MCP) servers. It stores structured audit data (JSON + Markdown), not runnable code: there is no build system, no test suite, and no lint step. "Correctness" here means conforming to the directory structure, naming conventions, and validation rules below — enforced at PR-review time, not by CI tooling.
The defining principle (see README.md) is radical transparency: every audit must document its full methodology, prompts, reasoning, and evidence so findings can be independently reproduced. Only open-source MCP servers are accepted, so audits remain reproducible. Simple "good/bad" verdicts without supporting rationale are rejected.
Repository Structure
audit-db/
├── audits/
│ └── [domain]/[org]/[repo]/ # e.g. audits/github.com/dbt-labs/dbt-mcp/
│ ├── metadata.json # Repo-level: mcp_classification, security_summary, audit_history
│ └── audits/
│ └── [auditor]-[date]-[seq]/ # e.g. panasenco-2026-02-02-001/
│ ├── audit-manifest.json # target (repo_url + commit_hash + version), findings_summary, tools_used
│ ├── security-assessment.md # Main human-readable report
│ ├── findings/ # One file per finding, by severity
│ │ └── [severity]-[num]-[name].md
│ ├── artifacts/ # Supporting evidence (code-samples/, diagrams, JSON)
│ └── raw-notes.md # Working notes
├── examples/ # Demo audits (e.g. finder-audit-demo-2025-08-20)
└── AUDIT_PR_VALIDATION_PROMPT.md # The workflow for validating incoming audit PRs (see below)
Current real audits live under audits/github.com/: dbt-labs/dbt-mcp, isaacwasserman/mcp-snowflake-server, makenotion/notion-mcp-server.
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 · 61 lines · 1,139 tokens per session scan A 90c21a21415b
audit-db CLAUDE.md is an instructions file published in the GitHub repository ModelContextProtocol-Security/audit-db (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,139 tokens to every session, about $0.0057 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.
Other instructions, from other repositories
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.
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).
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.
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).
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.
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.