Claude Desktop
Desktop · Freemium · Proprietary
Anthropic's official Claude AI desktop application. Supports MCP servers to extend functionality.
WindowsMacOS
AI Chatbot · Education & Learning
Chain of Draft Prompt Tool
brendancopley/mcp-chain-of-draft-prompt-tool
The MCP Chain of Draft (CoD) Prompt Tool is a powerful Model Context Protocol tool that enhances LLM reasoning by transforming standard prompts into either Chain of Draft (CoD) or Chain of Thought (CoT) format. Here's how it works.
Install
Client configuration
{
"mcpServers": {
"chain-of-draft-prompt-tool": {
"command": "/path/to/mcp-chain-of-draft-prompt-tool",
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}Environment variables
ANTHROPIC_API_KEYOPENAI_API_KEYMISTRAL_API_KEYMCP_LLM_PROVIDERMCP_OLLAMA_MODELMCP_CUSTOM_LLM_ENDPOINT- GitHub stars
- 8
- Author
- @brendancopley
- Category
- AI Chatbot, Education & Learning
- License
- MIT
- Updated
- Oct 6, 2026
About Chain of Draft Prompt Tool
:
This approach significantly improves reasoning quality while reducing token usage and maintaining high accuracy.
Features
Core Chain of Draft Implementation
Performance Analytics
Adaptive Word Limits
Comprehensive Example Database
Format Enforcement
Hybrid Reasoning Approaches
OpenAI API Compatibility
Tools (16)
Efficiency
Significantly reduced token usage (as little as 7.6% of standard CoT)
Speed
Faster responses due to shorter generation time
Flexibility
Applicable across various reasoning tasks and domains
chain_of_draft_solve
Solve a problem using Chain of Draft reasoning
math_solve
Solve a math problem with CoD
code_solve
Solve a coding problem with CoD
logic_solve
Solve a logic problem with CoD
get_performance_stats
Get performance stats for CoD vs CoT
get_token_reduction
Get token reduction statistics
analyze_problem_complexity
Analyze problem complexity
AnalyticsService
Tracks performance metrics across different problem domains and reasoning approaches
ComplexityEstimator
Analyzes problems to determine appropriate word limits
ExampleDatabase
Manages and retrieves examples, transforming CoT examples to CoD format
FormatEnforcer
Ensures reasoning steps adhere to word limits
ReasoningSelector
Intelligently chooses between CoD and CoT based on problem characteristics
analyticsDb
In-memory database for tracking performance metrics
Details on this page are taken from the project's README. Open README
Supported clients
Clients mentioned in this server's README:
Related MCP servers
n8n Secure Workflow Automation for Technical Teams
n8n-io/n8n
Fair-code platform to build and deploy AI agents and workflows. Combine a visual canvas with custom code, run it self-hosted or in the cloud, and connect to 1500+ integrations. AI automation you can trust with real work, from prototype to production.
repomix
yamadashy/repomix
Repomix is a tool that packs a codebase into an AI-friendly format, supporting local and remote repository processing and providing code compression, security checks and multiple output formats.
Inbox Zero AI MCP
elie222/inbox-zero
To help you spend less time in your inbox, so you can focus on what matters most.
figma-context-MCP
GLips/Figma-Context-MCP
Give Cursor and other AI-powered coding tools access to your Figma files with this Model Context Protocol server.
context7
upstash/context7
LLMs rely on outdated or generic information about the libraries you use. You get.
MCP Go
mark3labs/mcp-go
A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.