Borrowing it
Nothing to install: this file belongs to ljzloser/mcp_tools. 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/ljzloser/mcp_tools/master/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/ljzloser/mcp_toolsWrote 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/ljzloser/mcp_tools/copilot-instructions)<a href="https://agentmods.dev/instructions/ljzloser/mcp_tools/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/ljzloser/mcp_tools/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.01367 | $0.01367 |
| Opus 5 | $0.00683 | $0.00683 |
| Sonnet 5 | $0.00273 | $0.00273 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
mcp_tools copilot-instructions.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 6d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Tool Hub — 项目指南
架构
集成式 MCP 工具平台:服务端作为纯转发层暴露 tools/list 和 tools/call,所有功能以插件形式内置。
- 后端:
server/— FastMCP (MCP 协议) + FastAPI (管理 API, 端口 9020) + aiosqlite - 前端:
client/— PySide6 + qfluentwidgets (Fluent Design UI),通过 HTTP 管理 API 与后端通信 - Web 前端:
web/— Vue 3 SPA,构建到assets/web/,由 FastAPI 在/web/路径提供静态服务 - 插件:
plugins/— 每个插件 =BasePlugin(后端)+ 可选BasePluginWidget(UI Widget) - 协议层:
api/— 前后端共享的 Pydantic 模型 (protocol.py)、路由常量 (routes.py)、工具定义 (tool.py)、配置系统 (config.py)
通信分层:MCP 层走 stdio/SSE(AI 客户端),管理操作走 HTTP REST(UI 客户端)。
详细设计见 docs/DESIGN.md,开发计划见 docs/DEVPLAN.md。
构建与运行
uv sync # 安装依赖
uv run server.py # 启动服务 (stdio 模式)
uv run server.py --sse # 启动服务 (SSE 模式, 端口 9021)
uv run client.py # 启动管理 UI
pytest # 运行测试
cd web && npm run build # 构建 Web 前端 → assets/web/
创建新插件
- 在
plugins/下创建目录(不能以_或.开头),含__init__.py __init__.py导出PLUGIN_CLASS(必须)和WIDGET_CLASS(可选)- 后端继承
BasePlugin[ConfigModel],声明ToolDef类属性,实现handle_{tool_name} - 可选配置:声明
config_class,使用ConfigField子类定义字段 - 可选 Widget:继承
BasePluginWidget(QObject),实现get_name()+create_widget(parent) - 必须添加 README.md:每个插件目录下必须包含 README.md,描述工具列表和使用示例
参考模板:plugins/_template/
关键约定
- 路径管理:所有路径使用
utils/paths.py的paths对象,禁止硬编码路径 - 工具声明:用
ToolDef类属性声明工具(非字符串/装饰器),call_tool()自动分派到handle_{name} - 类型化 invoke:Widget 使用
invoke(PluginClass.tool_def, ArgsModel(...))而非字符串 - API 路径:使用
api/routes.py的Routes常量,不硬编码 URL - 响应解析:前端用
api/protocol.py的 Pydantic 模型解析 HTTP 响应 - 配置字段:
ConfigFielddescriptor 协议,self.config.key直接读写,Pylance 可推断类型 - 数据库时间:始终用
datetime('now', 'localtime'),不用 UTC - 无 Pillow 依赖:ICO 编码用纯 Python struct + Qt QImage/QBuffer
- 跨平台:所有平台专用代码必须用
if IS_WINDOWS:/if IS_LINUX:包裹,不直接调用平台 API - 工具返回:统一用
MCPToolResult(content=[{"type": "text", "text": "..."}], is_error=False/True) - 插件元数据:
meta属性返回PluginMeta(name, display_name, version, description, author, icon)
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.
- 6d ago First seen · 71 lines · 1,367 tokens per session scan A 9800b2c79dbe
mcp_tools copilot-instructions.md is an instructions file published in the GitHub repository ljzloser/mcp_tools (4 stars, last pushed 2mo ago), licensed MIT. It adds 1,367 tokens to every session, about $0.0068 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
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.
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).
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).
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.
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.