Borrowing it
Nothing to install: this file belongs to NateYeh/mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NateYeh/mcp-server/main/AGENTS.mdgit clone --depth 1 https://github.com/NateYeh/mcp-serverWrote 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.
[](https://agentmods.dev/instructions/nateyeh/mcp-server/agents-md)<a href="https://agentmods.dev/instructions/nateyeh/mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/nateyeh/mcp-server/agents-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.
<a href="https://agentmods.dev/instructions/nateyeh/mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/nateyeh/mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02395 | $0.02395 |
| Opus 5.5 | $0.00958 | $0.00958 |
| Sonnet 5.5 | $0.00479 | $0.00479 |
| Haiku 4.5 | $0.00239 | $0.00239 |
Grade A, and why
mcp-server AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST http://127.0.0.1:30096/mcp \ How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — mcp-server 專案指南
本檔案供 AI 與開發者快速進入狀況。詳細設計說明見 docs/ARCHITECTURE.md。
專案概述
MCP (Model Context Protocol) Server:以 FastAPI 提供 /mcp HTTP 端點,讓 LLM 客戶端
(如 Claude Code、Claude Desktop)能呼叫本機工具。目前僅提供 execute_shell(Linux Shell 命令執行)。
客戶端連接方式(Claude Code 原生 HTTP;Claude Desktop 需 mcp-remote 橋接)詳見 README 第 4 節。
- 版本:4.0.0
- Python:>= 3.10
- 執行方式:本地直接執行(無容器化部署)
- 認證:單一
AUTH_KEY(Bearer Token)
目錄結構
mcp-server/
├── src/mcp_server/
│ ├── __main__.py # 入口:日誌初始化、顯示 AUTH_KEY、啟動 uvicorn
│ ├── app.py # FastAPI 應用、/mcp 路由、MCP 協議分發
│ ├── config.py # 全域配置(AUTH_KEY、路徑、伺服器、執行限制)
│ ├── security.py # Bearer Token 驗證(hmac.compare_digest)
│ ├── schemas.py # MCPError(協議層錯誤)
│ ├── utils.py # format_tool_result()(ExecutionResult → MCP 回應)
│ ├── base/
│ │ └── logging_config.py # 統一日誌(console 彩色 + RotatingFileHandler)
│ ├── tools/
│ │ ├── __init__.py # 動態掃描目錄、自動註冊所有工具
│ │ ├── base.py # ToolRegistry 單例與 @registry.register
│ │ ├── schemas.py # ExecutionResult(工具回傳格式)
│ │ └── execute_shell/ # 目前唯一的工具
│ └── start.sh # 啟動腳本(安裝 mcp_server 後執行 python -m mcp_server)
├── docs/
│ ├── ARCHITECTURE.md # 詳細架構與開發範式
│ └── SELF_HEALING_MEMO.md # 故障排除備忘錄
├── .env.example # 環境變數範本
├── pyproject.toml # 套件依賴與工具設定(ruff / pyright);版本號唯一來源
└── workspace/ # 執行工作目錄(服務啟動時建立並清空,不進版控)
認證機制
- 金鑰來源:環境變數
AUTH_KEY。 - 未設定時:
config.py以secrets.token_urlsafe(32)隨機產生,僅存在於記憶體,__main__.py會於啟動時在 console 顯示;重啟即變更。 - 客戶端必須帶:
Authorization: Bearer <AUTH_KEY>。- 缺少或格式錯誤 →
401 - 金鑰不符 →
403
- 缺少或格式錯誤 →
- 驗證邏輯在
security.py的verify_api_key(),使用hmac.compare_digest常數時間比較。 - 失敗次數限制:同一來源 IP 於 60 秒內失敗達 10 次即回
429(Retry-After: 60),避免暴力嘗試。 - 已移除多金鑰(
MCP_API_KEYS)、Tool 權限白名單/排除清單與 Gmail 帳號綁定機制。
安全模型
- 唯一的存取控制是
AUTH_KEY(加上監聽位址)。本服務的設計目的就是執行任意 shell, 因此不提供命令黑名單——子字串黑名單容易被引號、變數、$IFS等方式繞過,只會給人錯誤的安全感。 - 因此:
AUTH_KEY等同於機器上的 shell 權限,務必只使用於可信任網段(建議MCP_HOST=127.0.0.1), 且不得寫進版控。 - 日誌不記錄金鑰本身(Authorization 格式錯誤時僅記錄 scheme)。
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.
- 5d ago Changed 1c610d5e68ac
- 10d ago First seen · 146 lines · 2,395 tokens per session scan A d45df933a5fd
mcp-server AGENTS.md is an instructions file published in the GitHub repository NateYeh/mcp-server (0 stars, last pushed 6d ago), licensed MIT. It adds 2,395 tokens to every session, about $0.0096 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-07.
Other instructions, from other repositories
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
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, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.