agentmods.dev

mcp-security-scanner CLAUDE.md

mcp-security-scanner CLAUDE.md is an instructions file for coding agents from badchars/mcp-security-scanner. It costs 442 tokens per session, scanned A, original, MIT.

Instructions for an MCP security scanner: a local tool that checks MCP servers and their source code for security weaknesses. It covers runtime inspection, code analysis, configuration checks, dependency checks, and OWASP MCP Top 10 mapping.

In plain words
What is it for?
It is for examining live server capabilities, scanning source code, auditing client configuration, checking dependencies, and organizing findings by security category.
Why use it?
It helps developers inspect an MCP server for vulnerabilities and configuration or dependency risks before relying on it.

Instructions file

not rated 5 3d ago A scan 442 tokens original MIT
View the source file badchars/mcp-security-scanner npmjs.com
Install

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.

agentmods
npx agentmods add instructions/badchars/mcp-security-scanner/claude-md
Clone the repo
git clone --depth 1 https://github.com/badchars/mcp-security-scanner

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 mcp-security-scanner CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/badchars/mcp-security-scanner/claude-md.svg)](https://agentmods.dev/instructions/badchars/mcp-security-scanner/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/badchars/mcp-security-scanner/claude-md"><img src="https://agentmods.dev/badge/instructions/badchars/mcp-security-scanner/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 442 This file is loaded in full into every session.
When invoked 442 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00442 $0.00442
Opus 5 $0.00221 $0.00221
Sonnet 5 $0.00088 $0.00088
Haiku 4.5 $0.00044 $0.00044

Measured 5d ago against content hash cb2d6552a141, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcp-security-scanner 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 5d 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 · 39 lines

What it actually says

mcp-security-scanner — MCP Security Scanner

Overview

43-tool MCP server + CLI for scanning MCP servers and their source code for security vulnerabilities. Runtime inspection, AST-based static analysis, config audit, dependency analysis. OWASP MCP Top 10 compliance mapping. 100% local, zero external API calls.

Architecture

  • Runtime: Bun 1.3.9+ (dev), Node.js (publish)
  • Dependencies: @modelcontextprotocol/sdk, ts-morph, zod (3 runtime deps only)
  • Transport: stdio only
  • Pattern: Each category in own directory under src/, tools registered in src/protocol/tools.ts

Key Rules

  • TypeScript strict mode, English code/comments
  • Every tool schema field must have .describe()
  • Import paths use .js extension (ESM)
  • Zero external API calls — all analysis runs locally
  • Finding IDs follow pattern: CATEGORY-CHECK-NNN (e.g. SAST-CMD-001, RT-POISON-003)

Tool Categories (43 tools)

  • rt_ — Runtime Inspection (11 tools): connect to live MCP servers, inspect capabilities
  • sast_ — Static Analysis (12 tools): AST-based code scanning via ts-morph
  • cfg_ — Config Audit (7 tools): parse and audit MCP client configs
  • dep_ — Dependency Analysis (7 tools): lockfile parsing, typosquat detection
  • report_ — Reports (4 tools): markdown, SARIF, JSON, full audit orchestrator
  • scanner_ — Meta (2 tools): check listing, OWASP mapping

Commands

bun install                          # Install deps
bun run dev                          # Dev mode (watch)
bun run build                        # Build for npm
bun run src/index.ts --help          # CLI help
bun run src/index.ts --list          # List all tools
bun run src/index.ts --tool <name> '<json>'  # Run single tool
bun run src/index.ts --full-audit ./path     # Full security audit
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. 5d ago First seen · 39 lines · 442 tokens per session scan A cb2d6552a141

Subscribe to this mod's changes

mcp-security-scanner CLAUDE.md is an instructions file published in the GitHub repository badchars/mcp-security-scanner (5 stars, last pushed 3d ago), licensed MIT. It adds 442 tokens to every session, about $0.0022 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.

Securityai-securitybunclaudemcpmcp-serverowasp
Related

Other instructions, from other repositories

trustmcp CLAUDE.md

Instructions for v0idw4lker/trustmcp, a project described as: Free, open-source security scanner for MCP servers, static analysis, live dynamic probing, auth posture detection, and SARIF/JSON reporting with A-F scoring mapped to OWASP MCP Top 10.

v0idw4lker/trustmcp · 141 tokens

aigis CLAUDE.md

Claude Code instructions for killertcell428/aigis, covering aigis — project guidelines, zenn記事管理（zenn cli + github連携）, ディレクトリ構成, 記事の作成 and プレビュー.

killertcell428/aigis · 1,668 tokens

assay CLAUDE.md

Claude Code instructions for Rul1an/assay, covering assay - ai agent context, what is assay?, workspace structure, key commands and cli entry points.

Rul1an/assay · 4,570 tokens

Agent-Security-Regression-Harness AGENTS.md

Instructions for OWASP/Agent-Security-Regression-Harness, covering ai agent guide: owasp agent security regression harness, project overview, architecture, contribution workflow and what needs doing.

OWASP/Agent-Security-Regression-Harness · 927 tokens

calc-mcp CLAUDE.md

Claude Code instructions for coo-quack/calc-mcp, covering project rules, tech stack, commands, project structure and tool architecture.

coo-quack/calc-mcp · 1,417 tokens

rosetta CLAUDE.md

Instructions for tikoci/rosetta, covering rosetta, project documentation, where does this go?, instruction routing and fast pointers.

tikoci/rosetta · 1,455 tokens