Files
nexus/wiki/concepts/Sequential-Thinking.md
2026-04-22 16:03:25 +08:00

35 lines
1.2 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
title: "Sequential Thinking"
type: concept
tags: [ai, mcp, reasoning, agent]
sources: []
last_updated: 2026-04-22
---
## Overview
Sequential Thinking 是 MCP 工具之一,支持逻辑推理与分步执行任务,通过逐步拆解复杂问题来优化 AI 模型的思考与响应过程,提升 AI 决策质量和沟通效率。
## Aliases
- 序列思考
- 逐步推理
- Step-by-step Reasoning
## Key Characteristics
- **分步拆解**:将复杂任务分解为多个可管理的步骤
- **逻辑链**:每一步都有清晰的推理逻辑和上下文
- **工具协同**:可与其他 MCP 工具(如热点新闻服务)相互调用、协同工作
- **可追溯**:推理过程透明,便于审查和修正
## Usage in MCP Context
- 在 Cursor Composer 的 Agent 模式下通过提示词触发
- 自动执行工具链并返回处理后的精准结果
- 适用于需要多步骤推理的复杂任务场景
## Connections
- [[MCPModel Context Protocol]] — Sequential Thinking 的实现载体
- [[Agent模式]] — 触发 Sequential Thinking 的交互环境
- [[Tool Calling]] — Sequential Thinking 依赖的工具调用机制
## Sources
- [[mcp在cursor中的集成与应用详解]]