# Chain of Thought

> Use this tool when you need to provide transparent and step-by-step reasoning for AI-generated answers, solving problems of trust and explainability in large language models. It takes in user queries and model outputs, and returns a stream of raw reasoning tokens that reveal the model's thinking process. Ideal for applications where understanding the "why" behind AI decisions is crucial, such as education, research, or high-stakes decision-making.

Canonical page: https://skillsregistry.net/skills/beverm2391-chain-of-thought  
JSON: https://api.skillsregistry.net/v1/skills/beverm2391-chain-of-thought

## Description

A Chain of Thought MCP server that exposes raw reasoning tokens from large language models through Groq's API. The server captures and streams the model's thinking process by intercepting content within <think> tags, allowing AI assistants to reveal their step-by-step reasoning before providing final answers. Built with FastMCP and supporting models like Qwen and DeepSeek, it enables more transparent AI interactions where users can see how the model arrives at conclusions rather than just receiving the final output.

## Trust

- **Trust score (0–1):** 0.91
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

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

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/beverm2391-chain-of-thought)
- **Repository:** <https://github.com/beverm2391/chain-of-thought-mcp-server>

## 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": "beverm2391-chain-of-thought"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/beverm2391-chain-of-thought` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/beverm2391-chain-of-thought/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