sequential-thinking
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseSequential Thinking
Sequential Thinking
Enables structured problem-solving through iterative reasoning with revision and branching capabilities.
通过具备修正和分支能力的迭代推理,实现结构化问题解决。
Core Capabilities
核心能力
- Iterative reasoning: Break complex problems into sequential thought steps
- Dynamic scope: Adjust total thought count as understanding evolves
- Revision tracking: Reconsider and modify previous conclusions
- Branch exploration: Explore alternative reasoning paths from any point
- Maintained context: Keep track of reasoning chain throughout analysis
- 迭代推理:将复杂问题拆解为一系列连续的思考步骤
- 动态范围调整:随着对问题的理解深入,调整总思考步骤数
- 修正追踪:重新审视并修改之前的结论
- 分支探索:从任意节点探索替代推理路径
- 上下文保持:在整个分析过程中追踪推理链
When to Use
使用场景
Use when:
mcp__reasoning__sequentialthinking- Problem requires multiple interconnected reasoning steps
- Initial scope or approach is uncertain
- Need to filter through complexity to find core issues
- May need to backtrack or revise earlier conclusions
- Want to explore alternative solution paths
Don't use for: Simple queries, direct facts, or single-step tasks.
在以下场景使用:
mcp__reasoning__sequentialthinking- 问题需要多个相互关联的推理步骤
- 初始范围或解决方法不明确
- 需要从复杂情况中筛选出核心问题
- 可能需要回溯或修正早期结论
- 希望探索替代解决方案路径
不适用场景:简单查询、直接事实获取或单步骤任务。
Basic Usage
基础用法
The MCP tool accepts these parameters:
mcp__reasoning__sequentialthinkingMCP工具接受以下参数:
mcp__reasoning__sequentialthinkingRequired Parameters
必填参数
- (string): Current reasoning step
thought - (boolean): Whether more reasoning is needed
nextThoughtNeeded - (integer): Current step number (starts at 1)
thoughtNumber - (integer): Estimated total steps needed
totalThoughts
- (字符串):当前推理步骤内容
thought - (布尔值):是否需要更多推理步骤
nextThoughtNeeded - (整数):当前步骤编号(从1开始)
thoughtNumber - (整数):预估的总步骤数
totalThoughts
Optional Parameters
可选参数
- (boolean): Indicates this revises previous thinking
isRevision - (integer): Which thought number is being reconsidered
revisesThought - (integer): Thought number to branch from
branchFromThought - (string): Identifier for this reasoning branch
branchId
- (布尔值):标识当前步骤是否为修正之前的思考
isRevision - (整数):正在重新审视的步骤编号
revisesThought - (整数):分支起始的步骤编号
branchFromThought - (字符串):此推理分支的唯一标识
branchId
Workflow Pattern
工作流模式
1. Start with initial thought (thoughtNumber: 1)
2. For each step:
- Express current reasoning in `thought`
- Estimate remaining work via `totalThoughts` (adjust dynamically)
- Set `nextThoughtNeeded: true` to continue
3. When reaching conclusion, set `nextThoughtNeeded: false`1. Start with initial thought (thoughtNumber: 1)
2. For each step:
- Express current reasoning in `thought`
- Estimate remaining work via `totalThoughts` (adjust dynamically)
- Set `nextThoughtNeeded: true` to continue
3. When reaching conclusion, set `nextThoughtNeeded: false`Simple Example
简单示例
typescript
// First thought
{
thought: "Problem involves optimizing database queries. Need to identify bottlenecks first.",
thoughtNumber: 1,
totalThoughts: 5,
nextThoughtNeeded: true
}
// Second thought
{
thought: "Analyzing query patterns reveals N+1 problem in user fetches.",
thoughtNumber: 2,
totalThoughts: 6, // Adjusted scope
nextThoughtNeeded: true
}
// ... continue until donetypescript
// First thought
{
thought: "Problem involves optimizing database queries. Need to identify bottlenecks first.",
thoughtNumber: 1,
totalThoughts: 5,
nextThoughtNeeded: true
}
// Second thought
{
thought: "Analyzing query patterns reveals N+1 problem in user fetches.",
thoughtNumber: 2,
totalThoughts: 6, // Adjusted scope
nextThoughtNeeded: true
}
// ... continue until doneAdvanced Features
高级功能
For revision patterns, branching strategies, and complex workflows, see:
- Advanced Usage - Revision and branching patterns
- Examples - Real-world use cases
关于修正模式、分支策略和复杂工作流,请参考:
- 高级用法 - 修正与分支模式
- 示例 - 真实场景用例
Tips
使用技巧
- Start with rough estimate for , refine as you progress
totalThoughts - Use revision when assumptions prove incorrect
- Branch when multiple approaches seem viable
- Express uncertainty explicitly in thoughts
- Adjust scope freely - accuracy matters less than progress visibility
- 先对进行粗略估计,随着推进逐步细化
totalThoughts - 当假设被证明错误时,使用修正功能
- 当存在多种可行方案时,使用分支功能
- 在思考步骤中明确表达不确定性
- 自由调整范围——相比准确性,进度可见性更为重要