# Sequential Thinking Multi-Agent System

> Use this tool when you need to break down complex problems through structured thinking steps, requiring diverse expertise and comprehensive analysis. It implements a team of specialized AI agents working in parallel to process thoughts with greater depth than single-agent approaches, providing detailed guidance throughout the thinking process. The tool takes in complex problems as input and outputs a comprehensive, multi-disciplinary solution, making it ideal for use cases involving multi-step analysis and decision-making.

Canonical page: https://skillsregistry.net/skills/fradser-mas-sequential-thinking  
JSON: https://api.skillsregistry.net/v1/skills/fradser-mas-sequential-thinking

## Description

Sequential Thinking Multi-Agent System (MAS) implements a coordinated team of specialized AI agents to break down complex problems through structured thinking steps. Built by Frad LEE using the Agno framework and DeepSeek models, this server orchestrates a Team Coordinator, Strategic Planner, Researcher (with Exa search capabilities), Core Analyzer, Quality Controller, and Integration Specialist working in parallel to process thoughts with greater depth than single-agent approaches. The implementation supports revision steps, branching analysis paths, and provides detailed guidance throughout the thinking process, making it particularly valuable for multi-disciplinary problem solving requiring diverse expertise and comprehensive analysis.

## Trust

- **Trust score (0–1):** 0.24
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/fradser-mas-sequential-thinking)
- **Repository:** <https://github.com/fradser/mcp-server-mas-sequential-thinking>

## 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": "fradser-mas-sequential-thinking"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/fradser-mas-sequential-thinking` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/fradser-mas-sequential-thinking/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