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.
git clone --depth 1 https://github.com/Mr-chen-05/rules-2.1-optimizedWrote 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/rules/mr-chen-05/rules-2.1-optimized/mcp-unified-management)<a href="https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/mcp-unified-management"><img src="https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/mcp-unified-management/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/rules/mr-chen-05/rules-2.1-optimized/mcp-unified-management"><img src="https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/mcp-unified-management.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 | $0.04380 | $0.04380 |
| Opus 5 | $0.02190 | $0.02190 |
| Sonnet 5 | $0.00876 | $0.00876 |
| Haiku 4.5 | $0.00438 | $0.00438 |
Grade A, and why
mcp-unified-management 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 9d 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 — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🌐 MCP统一管理策略
一站式管理: 整合所有MCP相关功能，提供统一的检测、推荐、配置和同步服务
🎯 核心功能
1. 跨平台环境检测
支持的AI工具:
# 主流AI编辑器
Trae: "%USERPROFILE%\AppData\Roaming\Trae\User\mcp.json"
Trae_CN: "%USERPROFILE%\AppData\Roaming\Trae CN\User\mcp.json"
Cursor: "%USERPROFILE%\AppData\Roaming\Cursor\User\globalStorage\cursor.mcp\mcp_settings.json"
Claude: "%USERPROFILE%\AppData\Roaming\Claude\claude_desktop_config.json"
# 2024-2025年热门AI工具
Windsurf: "%USERPROFILE%\AppData\Roaming\Windsurf\User\mcp.json"
Replit: "%USERPROFILE%\.replit\mcp_config.json"
Sourcegraph_Cody: "%USERPROFILE%\AppData\Roaming\Code\User\globalStorage\sourcegraph.cody-ai\mcp_settings.json"
Continue_dev: "%USERPROFILE%\.continue\mcpServers\mcp.json"
# IDE集成AI助手
VSCode_Copilot: "%USERPROFILE%\AppData\Roaming\Code\User\mcp.json"
JetBrains_AI: "%USERPROFILE%\.jetbrains\mcp_config.json"
Tabnine: "%USERPROFILE%\AppData\Roaming\TabNine\mcp_config.json"
# 云端AI平台
Amazon_Q: "%USERPROFILE%\AppData\Roaming\AmazonQ\settings.json"
Gemini_Code_Assist: "%USERPROFILE%\.google\gemini-code-assist\mcp.json"
Qodo_Gen: "%USERPROFILE%\.qodo\mcp_config.json"
# 开源AI工具
Aider: "%USERPROFILE%\.aider\mcp_config.json"
CodeGeeX: "%USERPROFILE%\.codegeex\mcp_settings.json"
TabbyML: "%USERPROFILE%\.tabby\mcp_config.json"
Cline: "%USERPROFILE%\AppData\Roaming\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json"
# OpenAI系列工具
OpenAI_Codex: "%USERPROFILE%\.openai\codex_mcp.json"
OpenAI_Codex_CLI: "%USERPROFILE%\.codex\cli_mcp_settings.json"
# 腾讯AI工具
CodeBuddy: "%USERPROFILE%\AppData\Roaming\CodeBuddy\User\globalStorage\tencent.planning-genie\settings\codebuddy_mcp_settings.json"
CodeBuddy_CLI: "%USERPROFILE%\.codebuddy\cli_mcp_config.json"
# 新兴AI编辑器
Void: "%USERPROFILE%\.void\mcp_config.json"
Warp: "%USERPROFILE%\.warp\mcp_settings.json"
Zed: "%USERPROFILE%\.zed\mcp_config.json"
# 高级AI助手
Refact_ai: "%USERPROFILE%\.refact\mcp_settings.json"
Jules_Google: "%USERPROFILE%\.jules\mcp_config.json"
Junie_JetBrains: "%USERPROFILE%\.junie\mcp_settings.json"
Kilo_Code: "%USERPROFILE%\.kilo\mcp_config.json"
Kodu: "%USERPROFILE%\.kodu\mcp_settings.json"
MarsCode: "%USERPROFILE%\.marscode\mcp_config.json"
Melty: "%USERPROFILE%\.melty\mcp_settings.json"
Memex: "%USERPROFILE%\.memex\mcp_config.json"
Mentat: "%USERPROFILE%\.mentat\mcp_settings.json"
检测机制:
自动扫描: 检测所有已安装的AI工具
- 主流编辑器: Trae, Cursor, Claude
- 热门AI工具: Windsurf, Replit, Sourcegraph Cody, Continue.dev
- IDE集成: VSCode Copilot, JetBrains AI, Tabnine
- 云端平台: Amazon Q, Gemini Code Assist, Qodo Gen
- 开源工具: Aider, CodeGeeX, TabbyML, Cline
- OpenAI系列: OpenAI Codex, Codex CLI
- 腾讯AI工具: CodeBuddy, CodeBuddy CLI
- 新兴编辑器: Void, Warp, Zed
- 高级助手: Refact.ai, Jules, Junie, Kilo Code, Kodu, MarsCode, Melty, Memex, Mentat
配置分析: 分析各平台MCP服务器配置
- 配置文件格式兼容性检查
- MCP服务器版本兼容性验证
- 工具特定配置项验证 (如Trae的disabled字段)
差异识别: 识别配置不一致和缺失项
- 跨平台配置同步状态
- 缺失的核心MCP服务器
- 工具特定功能缺失
性能评估: 分析服务器性能和可用性
- MCP服务器响应时间
- 内存使用情况
- 错误率统计
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.
- 9d ago First seen · 421 lines · 4,380 tokens per session scan A 525c07e131d9
mcp-unified-management is a cursor rule published in the GitHub repository Mr-chen-05/rules-2.1-optimized (173 stars, last pushed 10mo ago), licensed MIT. It adds 4,380 tokens to every session, about $0.0219 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 2026-08-30.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.