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-intelligent-strategy)<a href="https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/mcp-intelligent-strategy"><img src="https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/mcp-intelligent-strategy.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 | $0.05351 | $0.05351 |
| Opus 5 | $0.02676 | $0.02676 |
| Sonnet 5 | $0.01070 | $0.01070 |
| Haiku 4.5 | $0.00535 | $0.00535 |
Grade A, and why
mcp-intelligent-strategy 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 8d 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 — 604 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧠 MCP工具智能使用策略
🎯 核心原则
MCP优先原则: AI助手必须优先使用MCP工具，实现高效的任务执行和工具协同。
注意: MCP环境检测、配置管理、跨平台同步等功能已整合到 MCP统一管理策略 中。本策略专注于MCP工具的智能使用。
🎯 核心策略原则
智能系统集成优先
系统协同策略:
超级大脑系统:
- 统一的智能管理入口和决策支持
- 项目状态感知和上下文分析
- 自动化工作流编排和优化
- 持续学习和性能改进
项目管理集成:
- 五阶段生命周期严格管理
- 阶段约束和切换条件检查
- 完整工作流和质量保证
- 成功指标和效果评估
记忆系统协同:
- 多层次记忆架构和智能检索
- 自动记录和上下文感知
- 经验积累和知识管理
- 个性化服务和预测分析
推荐引擎集成:
- 多维度智能推荐算法
- 关键词匹配和语义理解
- 学习优化和反馈循环
- 个性化定制和效果评估
🔧 MCP工具使用优先级
工具选择策略:
强制优先级:
1. 智能检测MCP配置状态 (自动调用检测脚本)
2. 扫描可用MCP工具
3. 评估任务适配度
4. 选择最优工具组合
5. 执行并监控效果
自动脚本执行:
触发条件:
- 任务涉及文件操作时
- 需要跨平台MCP分析时
- 用户询问MCP状态时
- 检测到配置问题时
执行流程:
- 检查项目中是否存在mcp-tools/mcp-cross-platform-sync.ps1
- 如果存在，静默执行 -Action detect
- 策略引用: 默认遵循“检测复用与跳过 / 缓存复用”策略；详细参数与覆盖条件请参见 P2-intelligent-system/mcp-zero-config-detection.mdc
- 解析输出结果，整合到AI决策中
- 基于检测结果优化MCP工具选择
核心工具优先级:
Tier_1: server-filesystem, codebase-retrieval
Tier_2: server-github, mcp-feedback-enhanced, context7
Tier_3: 数据库工具, 自动化工具, 视觉AI工具
切换条件:
- MCP工具不可用 → 使用备选方案
- 功能不足 → 组合多个工具
- 性能问题 → 动态调整策略
效率优先原则
工具选择策略:
智能编排优先:
1. 基于项目阶段的自动工具选择
2. 上下文感知的工具组合优化
3. 历史成功模式的智能复用
4. 实时性能监控和动态调整
渐进式配置:
阶段1: 核心工具 (文件系统、代码搜索)
阶段2: 协作工具 (GitHub、反馈系统)
阶段3: 高级工具 (视觉AI、自动化)
阶段4: 定制工具 (项目特定需求)
传统优先级:
1. 高效率工具组合 (减少调用次数)
2. 专用工具优于通用工具
3. 批量操作优于单次操作
4. 缓存结果优于重复查询
避免策略:
- 重复的文件读取操作
- 不必要的搜索和检索
- 过度细分的工具调用
- 低效的工具组合使用
- 忽略智能系统的推荐和优化
🎯 MCP工具优先使用原则
1. 任务开始时的强制检查
每个任务开始时，必须执行：
1. 立即扫描所有可用的MCP工具
2. 识别任务类型和最适合的MCP工具
3. 评估MCP工具vs通用方法的效率差异
4. 优先选择MCP工具方案执行
2. MCP工具选择策略 4
选择原则: 基于任务特性和工具能力进行最优MCP工具选择。
MCP工具选择矩阵:
任务类型匹配:
文件操作:
- 首选: server-filesystem
- 适用: 所有文件读写、目录操作
- 优势: 高性能、批量操作
代码检索:
- 首选: codebase-retrieval
- 适用: 语义搜索、代码分析
- 优势: 智能理解、精确匹配
GitHub操作:
- 首选: server-github
- 适用: 仓库管理、PR、Issue
- 优势: 原生API、完整功能
用户交互:
- 首选: mcp-feedback-enhanced
- 适用: 复杂决策、确认操作
- 优势: 结构化反馈、超时处理
网页调试:
- 首选: chrome-devtools (CDP)
- 适用: 前端网络异常、控制台错误、DOM变更跟踪、性能分析
- 优势: 原生浏览器调试能力、精准事件监控
测试自动化:
- 首选: Playwright
- 适用: 端到端测试、跨浏览器自动化、回归测试
- 优势: 高可靠性、多浏览器支持、并行执行
知识管理:
- 默认建议: context7（文档与知识检索与管理）+ Recorder（记录员系统）
- 可选: server-memory（用于语义模糊检索或跨项目/跨时间聚合）
- 优势: context7统一知识入口与检索；Recorder精准归档与回溯；Memory语义聚合与跨范围检索
备选方案:
- 通用工具: MCP工具不可用时
- 手动操作: 一次性简单任务
- 混合方案: 复杂场景需要多工具配合
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.
- 8d ago First seen · 604 lines · 5,351 tokens per session scan A 8e60213ffeaf
mcp-intelligent-strategy 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 5,351 tokens to every session, about $0.0268 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-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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.