The MCP Chain of Draft (CoD) Prompt Tool is a powerful server that enhances LLM reasoning by transforming standard prompts into structured Chain of Draft or Chain of Thought formats. This approach significantly improves reasoning quality while reducing token usage and maintaining high accuracy.
# Clone the repository
git clone https://github.com/brendancopley/mcp-chain-of-draft-prompt-tool.git
cd mcp-chain-of-draft-prompt-tool
# Install dependencies
pip install -r requirements.txt
# Configure API key in .env file
echo "ANTHROPIC_API_KEY=your_api_key_here" > .env
# Run the server
python server.py
# Clone the repository
git clone https://github.com/brendancopley/mcp-chain-of-draft-prompt-tool.git
cd mcp-chain-of-draft-prompt-tool
# Install dependencies
npm install
# Configure API key in .env file
echo "ANTHROPIC_API_KEY=your_api_key_here" > .env
# Build and run the server
npm run nx build
npm start
# For development with auto-reload
npm run dev
This tool supports a "Bring Your Own LLM" approach:
# For Anthropic Claude
export ANTHROPIC_API_KEY=your_key_here
# For OpenAI
export OPENAI_API_KEY=your_key_here
# For Mistral AI
export MISTRAL_API_KEY=your_key_here
# First install Ollama
curl https://ollama.ai/install.sh | sh
# Pull your preferred model
ollama pull llama2
# or
ollama pull mistral
# Configure the tool to use Ollama
export MCP_LLM_PROVIDER=ollama
export MCP_OLLAMA_MODEL=llama2 # or your chosen model
# Point to your local model API
export MCP_LLM_PROVIDER=custom
export MCP_CUSTOM_LLM_ENDPOINT=http://localhost:your_port
Install Claude Desktop from claude.ai/download
Create or edit the Claude Desktop config file:
~/Library/Application Support/Claude/claude_desktop_config.json
Add the tool configuration (Python version):
{
"mcpServers": {
"chain-of-draft-prompt-tool": {
"command": "python3",
"args": ["/absolute/path/to/cod/server.py"],
"env": {
"ANTHROPIC_API_KEY": "your_api_key_here"
}
}
}
}
Or for the JavaScript version:
{
"mcpServers": {
"chain-of-draft-prompt-tool": {
"command": "node",
"args": ["/absolute/path/to/cod/index.js"],
"env": {
"ANTHROPIC_API_KEY": "your_api_key_here"
}
}
}
}
Restart Claude Desktop
You can also use the Claude CLI:
# For Python implementation
claude mcp add chain-of-draft-prompt-tool -e ANTHROPIC_API_KEY="your_api_key_here" "python3 /absolute/path/to/cod/server.py"
# For JavaScript implementation
claude mcp add chain-of-draft-prompt-tool -e ANTHROPIC_API_KEY="your_api_key_here" "node /absolute/path/to/cod/index.js"
Download and install Dive from their releases page
Configure the Chain of Draft tool in Dive's MCP settings:
{
"mcpServers": {
"chain-of-draft-prompt-tool": {
"command": "/path/to/mcp-chain-of-draft-prompt-tool",
"enabled": true,
"env": {
"ANTHROPIC_API_KEY": "your_api_key_here"
}
}
}
}
For the non-SEA version:
{
"mcpServers": {
"chain-of-draft-prompt-tool": {
"command": "node",
"args": ["/path/to/dist/index.js"],
"enabled": true,
"env": {
"ANTHROPIC_API_KEY": "your_api_key_here"
}
}
}
}
The following tools are available:
| Tool | Description |
|---|---|
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 |
from client import ChainOfDraftClient
# Create client with specific LLM provider
cod_client = ChainOfDraftClient(
llm_provider="ollama", # or "anthropic", "openai", "mistral", "custom"
model_name="llama2" # specify your model
)
# Use directly
result = await cod_client.solve_with_reasoning(
problem="Solve: 247 + 394 = ?",
domain="math"
)
print(f"Answer: {result['final_answer']}")
print(f"Reasoning: {result['reasoning_steps']}")
print(f"Tokens used: {result['token_count']}")
import { ChainOfDraftClient } from './lib/chain-of-draft-client';
// Create client with your preferred LLM
const client = new ChainOfDraftClient({
provider: 'ollama', // or 'anthropic', 'openai', 'mistral', 'custom'
model: 'llama2', // your chosen model
endpoint: 'http://localhost:11434' // for custom endpoints
});
// Use the client
async function solveMathProblem() {
const result = await client.solveWithReasoning({
problem: "Solve: 247 + 394 = ?",
domain: "math",
max_words_per_step: 5
});
console.log(`Answer: ${result.final_answer}`);
console.log(`Reasoning: ${result.reasoning_steps}`);
console.log(`Tokens used: ${result.token_count}`);
}
solveMathProblem();
You can use the MCP Inspector for testing and debugging:
# Start the MCP Inspector with the tool
npm run test-inspector
# Or run it manually
npx @modelcontextprotocol/inspector -e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY -- node dist/index.js
The Inspector will be available at http://localhost:5173 by default.
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "chain-of-draft-prompt-tool" '{"command":"node","args":["/absolute/path/to/cod/index.js"],"env":{"ANTHROPIC_API_KEY":"your_api_key_here"}}'See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:
{
"mcpServers": {
"chain-of-draft-prompt-tool": {
"command": "node",
"args": [
"/absolute/path/to/cod/index.js"
],
"env": {
"ANTHROPIC_API_KEY": "your_api_key_here"
}
}
}
}To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.json2. Add this to your configuration file:
{
"mcpServers": {
"chain-of-draft-prompt-tool": {
"command": "node",
"args": [
"/absolute/path/to/cod/index.js"
],
"env": {
"ANTHROPIC_API_KEY": "your_api_key_here"
}
}
}
}3. Restart Claude Desktop for the changes to take effect