plugin-development

A set of instructions for building or changing MCP Tool Hub plugins, which are add-ons that give an AI tool extra functions. It covers the required Python files, backend tools, optional user interface, and documentation.

In plain words
What is it for?
Use it when creating or updating a plugin in the plugins/ directory, including its Python backend, optional PySide6 desktop interface, and README.
Why use it?
It gives developers a consistent plugin structure and shows how to declare settings, inputs, metadata, and tool handlers. This reduces guesswork when adding or modifying plugins.

Instructions file for GitHub Copilot

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/ljzloser/mcp_tools/plugins
Clone the repo
git clone --depth 1 https://github.com/ljzloser/mcp_tools

Made for: GitHub Copilot.

Per session 1,539 This file is loaded in full into every session.
When invoked 1,539 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 $0.01539 $0.01539
Opus 5 $0.00770 $0.00770
Sonnet 5 $0.00308 $0.00308
Haiku 4.5 $0.00154 $0.00154

Measured 2d ago against content hash 4ea0bbe8d682, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plugin-development 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.

.github/instructions/plugins.instructions.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Tool Hub 插件开发指南

插件结构

每个插件目录包含:

  • __init__.py — 导出 PLUGIN_CLASSWIDGET_CLASS(可选)
  • backend.py — 插件后端逻辑
  • widget.py — 可选的 PySide6 UI 组件
  • README.md — 插件文档(必须)

目录名不能以 _. 开头。

后端模式

基本结构

from api.base_plugin import BasePlugin
from api.tool import ToolDef, MCPToolResult
from api.config import ConfigModel, StringField
from pydantic import BaseModel, Field

# 可选:配置模型
class MyPluginConfig(ConfigModel):
    api_key = StringField(default="", label="API 密钥", description="...")

# 工具参数模型
class MyToolArgs(BaseModel):
    input_text: str = Field(description="输入文本")

# 插件类
class MyPlugin(BasePlugin[MyPluginConfig]):
    config_class = MyPluginConfig
    
    # 工具声明 — 使用类属性 ToolDef
    my_tool = ToolDef(
        name="my_tool",
        args_model=MyToolArgs,
        description="工具描述"
    )
    
    @property
    def meta(self) -> PluginMeta:
        return PluginMeta(
            name="my_plugin",
            display_name="我的插件",
            version="1.0.0",
            description="插件功能描述",
            author="MCP Tool Hub",
            icon="🔧"
        )
    
    async def handle_my_tool(self, args: MyToolArgs) -> MCPToolResult:
        try:
            result = f"处理: {args.input_text}"
            return MCPToolResult(content=[{"type": "text", "text": result}])
        except Exception as e:
            return MCPToolResult(
                content=[{"type": "text", "text": f"错误: {e}"}],
                is_error=True
            )

工具声明规范

  • 使用 ToolDef 类属性(非装饰器)
  • name: 工具唯一名称,全局唯一
  • args_model: Pydantic BaseModel,用于参数验证和 JSON Schema 生成
  • description: 工具功能描述,供 AI 客户端使用

返回格式

统一使用 MCPToolResult:

# 成功
MCPToolResult(content=[{"type": "text", "text": "结果"}])

# 错误
MCPToolResult(content=[{"type": "text", "text": "错误信息"}], is_error=True)

访问配置

class MyPlugin(BasePlugin[MyPluginConfig]):
    async def handle_my_tool(self, args):
        # 直接通过 self.config 访问配置字段
        api_key = self.config.api_key

Read the full file on GitHub · 228 lines

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. 2d ago First seen · 228 lines · 1,539 tokens per session scan A 4ea0bbe8d682

Subscribe to this mod's changes

plugin-development is an instructions file published in the GitHub repository ljzloser/mcp_tools (4 stars, last pushed 2mo ago), licensed MIT. It adds 1,539 tokens to every session, about $0.0077 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens