# Chain of Draft (CoD) MCP Server

> Use this tool when you need to generate efficient and accurate intermediate reasoning outputs for tasks while minimizing token usage. The Chain of Draft (CoD) MCP Server implements a reasoning approach that reduces unnecessary output, making it ideal for applications where token conservation is crucial. It takes in tasks as input and produces minimalistic intermediate reasoning outputs, making it suitable for use cases where accuracy and efficiency are paramount.

Canonical page: https://skillsregistry.net/skills/stat-guy-chain-of-draft  
JSON: https://api.skillsregistry.net/v1/skills/stat-guy-chain-of-draft

## Description

Implements the Chain of Draft reasoning approach to generate minimalistic intermediate reasoning outputs while solving tasks, significantly reducing token usage while maintaining accuracy.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/cfynikwmy3)
- **Repository:** <https://github.com/stat-guy/chain-of-draft>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "stat-guy-chain-of-draft"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/stat-guy-chain-of-draft` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/stat-guy-chain-of-draft/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt