Chain of Draft
About
Enables iterative reasoning through structured drafts with explicit reasoning chains, allowing for focused critiques and targeted revisions to improve problem-solving quality through systematic refinement.
Details
- Author
- bsmi021
- Repository
- bsmi021/mcp-chain-of-draft-server
- GitHub stars
- 13
- Downloads
- 350
- License
- MIT License
- Categories
- Productivity, Developer Tools, AI, Project Management, Infrastructure, Other
Jump to
Iterative Reasoning: Systematic improvement through the Chain of Draft protocol
Thought History: Track and manage reasoning iterations
Branching Support: Focus reviews on specific reasoning steps
TypeScript Support: Full TypeScript implementation with Zod validation
Error Handling: Comprehensive error types and handling
Real-time Logging: Built-in debugging and monitoring system
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Chain of DraftCommand (node, npx, python, etc.)npxArguments-
Argument 1
-y -
Argument 2
@highlight/mcp-server
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Simple server configuration in initialize.ts:
const serverConfig = {
name: "chain-of-draft",
version: "1.0.0",
}
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"chain of draft": {
"env": {},
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}
}
}
Linux
{
"env": [],
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}
Macos
{
"env": [],
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}
Windows
{
"env": [],
"args": [
"/c",
"npx",
"-y",
"@highlight/mcp-server"
],
"command": "cmd"
}
MCP Chain of Draft Server 🧠
Chain of Draft Server is a powerful AI-driven tool that helps developers make better decisions through systematic, iterative refinement of thoughts and designs. It integrates seamlessly with popular AI agents and provides a structured approach to reasoning, API design, architecture decisions, code reviews, and implementation planning.
🌟 Features
Core Capabilities
Iterative Reasoning: Systematic improvement through the Chain of Draft protocol
Thought History: Track and manage reasoning iterations
Branching Support: Focus reviews on specific reasoning steps
TypeScript Support: Full TypeScript implementation with Zod validation
Error Handling: Comprehensive error types and handling
Real-time Logging: Built-in debugging and monitoring system
🚀 Getting Started
Prerequisites
Node.js >= 16.0.0
npm >= 8.0.0
Installation
1. Clone the repository:
git clone https://github.com/bsmi021/mcp-chain-of-draft-server.git
cd mcp-chain-of-draft-server
2. Install dependencies:
npm install
Configuration
Simple server configuration in initialize.ts:
const serverConfig = {
name: "chain-of-draft",
version: "1.0.0",
}
💡 Usage Examples
Chain of Draft Protocol
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"
};
🛠️ Development
Project Structure
src/
├── tools/ # Specialized Tools
│ ├── chainOfDraft/ # Core Protocol
│ └── index.ts / # Entry Point
├── utils/ # Utilities
└── index.ts # Entry Point
Starting Development Server
npm run dev
❓ FAQ
How does the Chain of Draft protocol work?
The protocol guides you through systematic improvement of your thinking through iterative drafts and focused critiques.
Can I customize the critique dimensions?
Yes! Each tool supports custom critique focuses tailored to your specific needs.
How many drafts should I plan for?
We recommend 3-5 drafts for most tasks, but you can adjust based on complexity.
🤝 Contributing
We welcome contributions! Please check our Contributing Guidelines.
👥 Community & Support
GitHub Issues - Report bugs or suggest features
Pull Requests - Submit your contributions
Documentation - Check our detailed docs
📝 License
MIT License - see the LICENSE file for details.
🙏 Acknowledgments
Thanks to our contributors and early adopters
Special thanks to the MCP community
Inspired by systematic reasoning methodologies
---
Made with 🧠 by @bsmi021
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





