Chain of Draft Thinking
MCP 链草稿服务器
Chain of Draft Server 是一款强大的 AI 驱动工具,它通过系统化、迭代式地完善思路和设计,帮助开发者做出更明智的决策。它能够与主流 AI 代理无缝集成,并提供结构化的推理、API 设计、架构决策、代码审查和实施规划方法。
🌟 功能
核心能力
迭代推理:通过草案链协议进行系统改进
思维史:跟踪和管理推理迭代
分支支持:重点回顾特定的推理步骤
TypeScript 支持:通过 Zod 验证实现完整的 TypeScript
错误处理:全面的错误类型和处理
实时日志记录:内置调试和监控系统
Related MCP server: Chain of Draft Prompt Tool
🚀 入门
先决条件
Node.js >= 16.0.0
npm >= 8.0.0
安装
克隆存储库:
git clone https://github.com/bsmi021/mcp-chain-of-draft-server.git
cd mcp-chain-of-draft-server安装依赖项:
npm install配置
在initialize.ts中进行简单的服务器配置:
const serverConfig = {
name: "chain-of-draft",
version: "1.0.0",
}💡 使用示例
草案协议链
const thoughtData = {
reasoning_chain: ["Initial analysis of the problem"],
next_step_needed: true,
draft_number: 1,
total_drafts: 3,
is_critique: true,
critique_focus: "logical_consistency"
};🛠️ 开发
项目结构
src/
├── tools/ # Specialized Tools
│ ├── chainOfDraft/ # Core Protocol
│ └── index.ts / # Entry Point
├── utils/ # Utilities
└── index.ts # Entry Point启动开发服务器
npm run dev❓ 常见问题解答
Chain of Draft 协议如何运作?
该协议将指导您通过迭代草稿和重点批评来系统地改进您的思维。
我可以自定义批评维度吗?
是的!每个工具都支持根据您的特定需求定制评论重点。
我应该计划多少份草稿?
我们建议大多数任务需要 3-5 个草稿,但您可以根据复杂性进行调整。
🤝 贡献
欢迎大家投稿!请查看我们的投稿指南。
👥 社区与支持
GitHub 问题 - 报告错误或建议功能
拉取请求 - 提交你的贡献
文档 - 查看我们的详细文档
📝 许可证
MIT 许可证 - 有关详细信息,请参阅LICENSE文件。
🙏 致谢
感谢我们的贡献者和早期采用者
特别感谢 MCP 社区
受到系统推理方法的启发
由 @bsmi021 使用 🧠 制作
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Related MCP Servers
- AlicenseCqualityAmaintenanceTransform your codebase into professional architectural decision records with intelligent AI analysis7518033MIT
- AlicenseNot gradedqualityCmaintenanceTransforms prompts into Chain of Draft (CoD) or Chain of Thought (CoT) format to enhance LLM reasoning quality while reducing token usage by up to 92.4%, supporting multiple LLM providers including Claude, GPT, Ollama, and local models.2519MIT
- AlicenseNot gradedqualityDmaintenancePersistent decision memory and contradiction detection for AI coding agents. Enforces architectural consistency across sessions — the agent cannot code until it loads prior decisions. Human resolves conflicts on a dashboard or in chat.1MIT
- AlicenseAqualityBmaintenanceA structured, persistent reasoning workspace for AI. 20 tools for thought chains, branching, revision, search, tagging, and SQLite session persistence that survives context window resets and server restarts.20722MIT
Related MCP Connectors
Agent-to-agent reasoning-as-a-service: chain-of-thought, analysis, and decision support.
AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/bsmi021/mcp-chain-of-draft-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server